Skip to main content
deleted 10 characters in body
Source Link

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|\Sigma\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and thecovariance of noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|\Sigma\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|\Sigma\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and covariance of noise matrix, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

added 5 characters in body
Source Link

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|H\|$$$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|\Sigma\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|H\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|\Sigma\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

added 164 characters in body
Source Link

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|H\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise.

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|H\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

Lets first assume $\zeta_i=0$ and ask the following:

  • under which conditions $w^*$ is a stable fixed point?

If it's not a stable fixed point for noise-free case, then you won't end up with a fixed mean or stationary distribution after adding additive noise. This means $w^*$ being a fixed point is a necessary condition for ergodicity. In the case of isotropic Gaussian noise, it might also be sufficient (needs checking)

Example

Consider 2-dimensional problem with the following covariance:

\begin{equation} \Sigma=\left( \begin{matrix} 1 & 0 \\ 0 & 2 \end{matrix} \right) \end{equation}

One condition on step size $\eta=\alpha$ which guarantees convergence

$$\frac{2}{\alpha}<\text{Tr}(\Sigma)+2\|H\|$$

This equation is derived in many places, ie 3.30 in Diniz "Adaptive Filtering". This produces the following condition on step size in our example: $$\alpha<\frac{2}{7}$$

However, this condition is too strict and larger values of $\alpha$ work. The necessary and sufficient condition turns out to be the following:

$$\alpha<\frac {4} {9 + \sqrt {17}}$$

I extend the expression above for a general Gaussian in this note. I haven't seen anyone else derive this, please correct me if this already occurs in literature.

General solution

For $x_i$ sampled from a zero-centered Gaussian with covariance $\Sigma$, the necessary and sufficient condition for $w^*$ to be a fixed point in a noiseless case is that

$$\alpha<\frac{2}{\rho(A)}$$

Where $\rho$ denotes spectral radius and $A$ is defined below. Let $s=(s_1, s_2, s_3, \ldots)$ be the eigenvalues of $\Sigma$, then \begin{equation}\label{defa} A= 2 \left( \begin{array}{cccc} s_1 & 0 & 0 & \ldots \\ 0 & s_2 & 0 & \ldots \\ 0 & 0 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) + \left( \begin{array}{cccc} s_1 & s_1 & s_1 & \ldots \\ s_2 & s_2 & s_2 & \ldots \\ s_3 & s_3 & s_3 & \ldots \\ \ldots & \ldots & \ldots & \ldots \end{array} \right) \end{equation}

I haven't found a simpler closed form expression for this, but a sequence of bounds can be derived by bounding spectral radius of $A$ with norm of $A^k$ for various values of $k$, discussion.

I suspect that convergence to fixed point in noiseless case also implies convergence to stationary distribution in the case of isotropic additive noise. In the case of non-isotropic noise, may need to consider the ratio of $\Sigma$ and the noise matrix instead of $\Sigma$, like is done in NQM paper

Existing results for non-Gaussian case:

It can be shown that in the case of 1 dimension and deterministic $x$, the following condition on $\alpha$ is necessary and sufficient for convergence \begin{equation}\label{supersimple} \alpha x^4 < 2 x^2 \end{equation}

Since we have $h=x^2$ for Hessian $h$, this reduces to the well known bound on convergent learning rate: $\alpha < 2/h$

In the case of stochastic x, the following is necessary and sufficient

\begin{equation}\label{eq:0} \alpha E[x^4] < 2 E[x^2] \end{equation}

For the case of $x$ being distributed as standard normal, this gives $2/(3h)$ for the largest learning rate, three times smaller than what's allowed in deterministic case

For the case of $d$ dimensions, the following is a sufficient condition, with $\prec$ indicating Loewner order\footnote{assumption A.6 in Bach paper

\begin{equation}\label{eq:1} \alpha E[xx'xx'] \prec E[xx'] \end{equation}

The right-hand side can be tightened to \begin{equation}\label{eq:1x} \alpha E[xx'xx'] \prec 2 E[xx'] \end{equation}

Bach, Deffosez2015 showed that the following optimization over symmetric matrices gives sufficient condition for convergence, and conjectured it to also be necessary (Lemma 1 of Defossez2015)

\begin{equation}\label{eq:2} \frac{1}{\alpha} < \sup_{A\in \mathcal{S}(R^d)} \frac{E[(x'Ax)^2]}{2 E[x'A^2 x] } \end{equation}

We can show this to be equivalent to the following positive semi-definite constraint \begin{equation}\label{eq:3} \alpha E[xx' \otimes xx'] \prec E[xx'\otimes I] + E[I\otimes xx'] \end{equation}

Most recently, Jain generalized last Eq to batch sizes beyond 1 and formally showed it to be a necessary condition for monotonic convergence. When applied to Gaussian case, this is equivalent to $\text{Tr}(\Sigma)+2\|H\|$ condition derived earlier.

added 1052 characters in body
Source Link
Loading
added 1052 characters in body
Source Link
Loading
added 2070 characters in body
Source Link
Loading
added 2070 characters in body
Source Link
Loading
Source Link
Loading