All Questions
Tagged with it.information-theory st.statistics
110 questions
0
votes
0
answers
50
views
General formula for Fisher information matrix reparameterization?
Prefacing apology for likely having unclear notation in the question and possible unclear concepts, because I'm not a mathematician.
The Fisher Information Matrix (FIM) for a multivariate normal ...
- 75
16
votes
1
answer
397
views
Examples of problems in statistics accessible only using information geometry
I am just curious if there are some examples of problems in statistics that are indeed accessible using information geometry while proofs completely avoiding geometry are unknown. In other words, ...
- 269
0
votes
0
answers
51
views
Upper bound on expectation of a convolution
Given probability densities $f, g\in L^p(\mathbb{R}^3), \ \forall p\geq 1$, with the same first and second moments
\begin{align} & \int_{\mathbb{R}^3} v f(v)\,dv = \int_{\mathbb{R}^3} v g(v)\,dv, \...
- 43
0
votes
0
answers
85
views
When is a family of distributions "closed" with respect to minimal sufficient statistics?
As in the title, I am interested in understanding how to express the idea that a parametric family of distribution is "closed" with respect to minimal sufficient statistics. Before giving ...
3
votes
0
answers
80
views
Seeking strong bounds on KL-divergence and martingales for a hypothesis-testing inequality
Let's say we have a finite set $\mathcal{O}$ of observations, and let $\mathcal{C}(\Delta\mathcal{O})$ denote the space of closed convex sets of probability distributions.
We have two hypotheses which ...
- 353
0
votes
1
answer
129
views
Reverse Pinsker's inequality for smooth density classes
Suppose we are given a class of probability density functions $\mathcal{F}$ so that for every $f \in \mathcal{F}$ we have $\alpha \leq f \leq \beta$ for some positive $\alpha, \beta \in \mathbb{R}_+$ ...
2
votes
0
answers
92
views
Construct a Bregman divergence from Wasserstein distance
I was wondering whether one has studied the Bregman divergence arising from a squared Wasserstein distance.
More precisely, let $\Omega\subset \mathbb{R}^d$ be a compact set and $c\in \Omega\times \...
- 503
0
votes
1
answer
107
views
What's the lower bound for this quantity?
Suppose $p$ is a discrete distribution with $n$ values and the random variable $x$ satisfies $\mathbb{E}_p[x] = 0$ and $|x| < \infty$. Given $\alpha \in (0,1)$, does there exist a lower bound for ...
- 49
2
votes
1
answer
214
views
Estimating means of multiple Gaussians
Let's say we have two Gaussian distributions $\mathcal{N}(\mu_1, \sigma^2I_d)$ and $\mathcal{N}(\mu_2, \sigma^2I_d)$. We are trying to get estimators $\hat \mu_1, \hat \mu_2$ to minimize the following ...
0
votes
0
answers
52
views
Classifier-specific lower bounds on the misclassification rate in binary classification
Consider a binary classification problem for $(X,Y)$, and let $\hat{f}$ be a proposed classifier. We wish to bound the misclassification rate $P(\hat{f}(X)\ne Y)$. There are many known lower bounds on ...
- 13
2
votes
0
answers
68
views
What is an efficient non-adaptive group testing scheme if the number of defectives, $d$, grows proportionally to the number of items, $n$?
Suppose that for some $p \in \left(0, 1\right)$ and some $n \in \mathbb{N}$, we have $n$ independent Bernoulli random variables, $X_{1}, X_{2}, \dots, X_{n}$, each with mean $p$. We shall call $X_{1}, ...
2
votes
1
answer
415
views
Bounding Kullback-Leibler
Suppose we have a probability distribution $P$ on a finite set $S$. We draw $N$ i.i.d. samples according to $P$ and use these samples to define an empirical distribution $R$. We measure the Kullback-...
- 3,979
3
votes
0
answers
93
views
Asymptotic approximation of Fisher information matrix for small Gaussian perturbation
Let
$$
X=Y/a+b+\epsilon Z,
$$
where $Y\sim\operatorname{Poisson}(\lambda)$ and $Z\sim\mathcal N(0,1)$ are independent. Also define $\theta=(\lambda,a,b,\epsilon)$. The Fisher information matrix
$$
...
1
vote
1
answer
93
views
An inequality relating $\ell_1$ distance of input and output of a Markov krnel
Let $K$ be a Markov kernel from $\mathcal{X}$ to $\mathcal{Y}$, i.e., $K(\cdot|x)$ is a probability measure on $\mathcal{Y}$ for all $x\in \mathcal{X}$.
Let $\mu$ and $\nu$ be two probability measures ...
- 1,109
1
vote
0
answers
48
views
Sample complexity of estimating a doubly stochastic matrix
Let $P\in\mathbb{R}^{n\times n}$ be a doubly-stochastic matrix. That is:
$$P(x,y)\geq 0,\quad \sum_xP(x,y)=1,\quad \sum_yP(x,y)=1.$$
I would like to know if lower and upper bounds on the sample ...
- 111
6
votes
2
answers
344
views
Entropy & difference between max and min values of probability mass
Let $X$ be a random variable with probability mass function $p(x) = \mathbb{P}[X = x]$.
I know entropy $H(X)$ of $X$ measures the uncertainty of $X$ and
a large value of $H(X)$ means $p(x)$ is nearly ...
- 163
1
vote
0
answers
34
views
Correlating two matrices $A,B$ with stochastic dependency structure imposed by cross-validation
Consider a labelled data set
$$D = \{(x_1, y_1),...,(x_n, y_n)\} $$
on which we want to evaluate a machine learning algorithm using $k$-fold cross validation with $m$ different random seeds. This ...
- 153
5
votes
0
answers
191
views
Divergence for Bhattacharya Information matrix
The Fisher information matrix (in the scalar parameter case) can be obtained from the Kullback-Leibler divergence by
$$g(\theta) = -\frac{\partial}{\partial \theta}\frac{\partial}{\partial \theta'}D(...
- 779
4
votes
0
answers
144
views
Exponential families closed under affine transformations
Let $(\Omega,\Sigma,\mu)$ be a probability space and let $\mathcal{M}$ be an exponential family of probability distributions for $\mu$ of the following form: There are $\varphi_1,\dots,\varphi_n:\...
- 5,405
4
votes
1
answer
415
views
What journal(s) do you recommend for submitting a paper on a topic that spans information theory and estimation theory?
I've written a paper that a) demonstrates an equivalence between conditional complexity $K$($Y$|$X$) in information theory and the random component of an effect size estimate $r_{xy}$, and then b) ...
- 183
2
votes
1
answer
294
views
An inequality in the optimality of Bayes' theorem
$\DeclareMathOperator\Ent{Ent}\newcommand{\prior}{\mathrm{prior}}\newcommand\Data{\mathrm{Data}}$I came across this paper on the optimality of Bayes' theorem
https://sinews.siam.org/Portals/Sinews2/...
- 23
2
votes
0
answers
132
views
A result of the covering number
Suppose $\mathcal{F} = \{f_x : x \in \mathbb{R}^d \}$ and each $f_x$ shares the same law $P$. If $\mathcal{F}$ is a class of uniformly bounded functions satisfying $L_r$-continuity, i.e. $\forall f \...
- 331
5
votes
1
answer
150
views
Kullback–Leibler chains
The following question was asked and then deleted by the post author:
Let $P$ and $Q$ be two probability distributions defined over the same space, with $KL(P \parallel Q) < \infty$. For $\epsilon ...
- 128k
1
vote
1
answer
135
views
KL-divergence and sub-$\sigma$-algebras
I am trying to understand if the following claim is true:
Let $P$, $Q$ be probability measures on $\mathcal{X}$. For any $\sigma$-algebra $\mathcal{G}$, with countably many atoms (sets with $\...
- 13
7
votes
1
answer
1k
views
reverse KL-divergence: Bregman or not?
I am having a little trouble getting my head around the two "directions" of the Kullback-Leibler divergence:
Definition (Kullback-Leibler divergence) For discrete probability distributions $...
- 101
0
votes
0
answers
171
views
A basic property of maximal correlation
Let $𝑋$ and $𝑌$ be random variables. Then the maximal correlation $\rho_{m}(X;Y)$ is defined as:
$$\rho_{m}(X;Y):=\max_{f,g}\mathbb{E}[f(X)g(Y)],$$
where the maximization is taken over real-valued ...
- 11
1
vote
0
answers
65
views
Normalizing constants preserve metric entropy
Suppose $\mathcal{F}=\left\{f\in L^2([a,b]): 0<\underline{c}\leq f\leq\overline{c} \right\}$. Consider the following transformation
$$\tilde{\mathcal{F}} := \left\{\frac{f}{\int f d\mu}: f\in \...
- 11
2
votes
1
answer
199
views
Do enough permutations of an initial set probably cover most permutations?
Fix $\alpha, \epsilon \in(0,1)$. Take $(S_n)_n$ to be any sequence of sets with each $S_n$ containing $ \lceil (n!)^\alpha\rceil$ permutations of $n$ elements. Also build another sequence of sets $(...
4
votes
1
answer
361
views
Information monotonicity of divergence => function of $f$-divergence
It is well-known that $f$-divergences defined on $\mathcal P(\mathcal X)$ where $\mathcal X$ is a measure space with $\sigma$-algebra $\mathcal B$ satisfy the property of information monotonicity:
...
- 203
1
vote
0
answers
212
views
A new notion of probability coupling
Let $X$ and $Y$ be two discrete random variables distributed according to $\mu$ and $\nu$, respectively. Consider the following optimization problems
$$\inf_{\pi\in \Pi(\mu, \nu)}\Pr(X\neq Y),$$
...
- 1,109
6
votes
1
answer
527
views
Can information be extracted more precisely using more random trials?
Write $n$ iid draws of $(x,y)$ as $(x^n, y^n)$. Fix $R\in (0,H(x))$. What is the min of $n^{-1}H(y^n|f(x^n))$ over maps $f$ with range $\lbrace 1,\dots,\exp nR\}$, taking $n\to \infty$?
7
votes
1
answer
660
views
Books to develop a unified view of statistics and information theory?
I hope to understand the connection between statistics and information theory in a deep philosophical sense.
I suppose the best place to start would be David MacKay's Information Theory, Inference, ...
- 73
2
votes
0
answers
217
views
Inequality on the Kullback-Leibler divergence
Let us define the arithmetic, geometric, and harmonic means of $x,y \in \mathbb{R}$ weighted by $\alpha =(\alpha_x,\alpha_y) \in [0,1]$, respectively as
\begin{equation}
a_\alpha(x,y) = \frac{\...
- 245
0
votes
2
answers
299
views
Statistical divergence
Does anyone know about a statistical divergence of this type?
\begin{equation}
\text{D}(P||Q) = \frac{1}{2} \left[\text{KL}(M||P) + \text{KL}(M||Q)\right]
\end{equation}
where $M = \frac{1}{2} [P+Q]$....
- 245
3
votes
2
answers
233
views
Lower bounding decoding error in a noisy adversarial channel
Problem description
Suppose we have a finite alphabet $\mathcal{X}$, where each letter $X \in \mathcal{X}$ indexes into some fixed set of distributions, $\{P_{1},\ldots,P_{|\mathcal{X}|}\}$. For ...
- 181
4
votes
1
answer
312
views
Given three distributions p, q and h. If KL(p||q) is large enough and KL(q||h) is small enough, does there exist a number N such that KL(p||h)>N?)
Given three distributions $p, q$ and $h$, assume we know that the Kullback-Leibler divergence obeys
$KL(p\Vert q)$ is large enough, say $KL(p\Vert q) > M$ where $M$ is large enough, and
$KL(q\Vert ...
- 77
2
votes
0
answers
396
views
Connecting Wasserstein distance with mutual information?
Suppose I have Markov chains:
$$X \rightarrow f(X) \rightarrow g(X)$$
$$Y \rightarrow f(Y) \rightarrow g(Y)$$
where it is known that minimizing the $\mathbb{E}(g(X)) - \mathbb{E}(g(Y))$ minimizes the ...
- 67
2
votes
1
answer
282
views
Convexity of exponential family
It is known that (given a $\sigma$-finite Borel reference measure $\nu$ on $\mathbb{R}$) the parameter space of an exponential family is convex in Euclidean space. However, my question is, for an the ...
- 5,405
3
votes
1
answer
737
views
Exponential deconvolution using the first derivative
There is an interesting observation using the first derivative to deconvolve an exponentially modified Gaussian:
The animation is here at terpconnect.umd.edu.
The main idea is that if we have an ...
- 879
3
votes
1
answer
167
views
Maximal correlation and independence
Let $X$ and $Y$ be random variables. Then the maximal correlation $\rho_m(X;Y)$ is defined as
$$ \rho_m (X;Y) := \max_{(f(X),g(Y))\in S} \mathbb{E} [f(X)g(Y)] $$
where $S$ is the collection of pairs ...
- 33
4
votes
1
answer
839
views
A balls into bins problem with combinatorial constraints
We are given $m$ balls and $n$ bins, with $m \ge n$. Each bin can contain at most $c$ balls (we assume that $c$ is an even integer). In a sequential fashion, at each time step, one ball is placed into ...
- 1,677
1
vote
0
answers
213
views
Jensen-Shannon Divergence of Sample Distributions
Given normal distributions with a single positional and variation parameter each, $p_1=\big[\mu_1, \sigma_1\big]$, $p_2=\big[\mu_2, \sigma_2\big]$, we define their Jensen-Shannon divergence as:
$$
\...
- 429
1
vote
1
answer
105
views
What is the distribution of a Cartesian power of a collection of iid uniform points? (renewed)
The following question was asked recently at https://mathoverflow.net/questions/326631/what-is-the-distribution-of-a-cartesian-power-of-a-collection-of-iid-uniform-poi :
Take a rectangle with ...
- 128k
1
vote
0
answers
180
views
Kullback-Leibler as a function of weights on a normal mixture
I'm interested in the Kullback-Leibler divergence on multimodal gaussian mixtures.
For positive, real weights $\sum_{1\leq k\leq m}w_k=\sum_{m+1\leq k\leq n}w_k=1$, univariate Gaussians $g_k\equiv g(...
- 429
2
votes
1
answer
1k
views
Mutual information between continuous and discrete variables from numerical data
I am looking for references/measures to estimate the mutual information between a continuous (C) and discrete (D) variable, given a real-world (i.e. finite sample) data set. C is uniformly distributed ...
- 21
7
votes
1
answer
231
views
Relation between the two possible KL divergences of two distributions
Given that I know $$D\left(P\parallel Q\right)<\alpha,$$ can I say anything about $D\left(Q\parallel P\right)$ in terms of an upper bound on it?
Also, given this upper bound on $D\left(P\parallel ...
- 503
3
votes
1
answer
355
views
Upper bounding the start of a distribution's CDF, given bounds on first moments
Take nonnegative random variables $X$ whose first $K$ moments have bounds:
$\mu^k\leq E[X^k]\leq c\mu^k$ for each $k=1,\dots,K$.
In this case what is an upper bound for $P(X\leq O(\mu))$?
I am ...
2
votes
0
answers
107
views
Does lattice mod preserve direction?
For high enough dimension $n$, the base cell of the Voronoi partition of a lattice $L_n$ in $\mathbb{R}^n$ picked randomly from the Siegel ensemble typically has some unit-ball-like properties: it ...
2
votes
1
answer
179
views
upper bound on power of neyman-pearson hypothesis test
Let $H_0$ and $H_1$ be two distributions. The Neyman-Pearson lemma says that of all rejection regions $R$ with fixed probability $\alpha$ under $H_0$, the one with maximal probability under $H_1$ is ...
- 133
3
votes
0
answers
178
views
Partitioning the coupons collected in the classical coupon collector's problem
Suppose that there is an urn containing $n$ different coupons, from which $m$ coupons are being collected, equally likely, with replacement.
Let $C(m)$ be the whole set of the $m$ collected coupons. ...
- 1,677