Questions tagged [learning-theory]
This tag is used for questions that are related with following branches: Statistical learning theory, Machine learning, Vapnik–Chervonenkis theory (VC theory) and all other branches that are studied and applied in the area of learning theory that involves various kinds of mathematics.
100 questions
1
vote
0
answers
75
views
VC-dimension of intersection
Let $A$ and $B$ be sets of real-valued functions on $X$. Are there any reasonably tight bounds on the VC-dimension of $A\cap B$ in terms of the VC-dimensions of $A$ and $B$?
- 5,407
2
votes
0
answers
71
views
How to naturally define an output space with certain properties
Consider the following regression problem $v=A(u) + \varepsilon$
for some operator $A:\mathcal{U} \rightarrow \mathcal{V}$ and some function spaces $\mathcal{U},\mathcal{V}$, mapping from $\mathcal{X}$...
- 51
0
votes
0
answers
70
views
VC dimension of full-dimensional closed polyhedral cone in $\mathbb R^d$
Consider a fixed set of vectors $\{x_i\}_{i\in[n]}$ in $\mathbb R^d$ and closed polyhedral cone $C = \{w \in \mathbb R^d : w^\top x_i \geq 0, \forall i \in [n]\}$ with full dimension i.e. $C$ contains ...
- 1
3
votes
2
answers
358
views
Minimax optimal multiple hypothesis test
Let us consider the following two-player game
between Chooser and Guesser.
There is a finite set $\Omega$
and $k$ probability distributions
on $\Omega$, denoted by $
\mathcal{P}
=\{P_1,\ldots,P_k\}
$.
...
- 6,541
3
votes
1
answer
108
views
When does the optimal model exist in learning theory?
In the context of learning theory, we usually have: data $(x,y)\sim P(x,y)$, with $x\in\mathcal{X}\subseteq\mathbb{R}^d$ and $y\in\mathcal{Y}\subseteq\mathbb{R}^k$, a hypothesis class $\mathcal{F}\...
- 199
1
vote
0
answers
65
views
Is learning easy in balls where all candidates hypotheses agree on the query?
Let $\mathcal{H}$ be ahypothesis class, $h\in \mathcal{H}$ be a function a model that maps an input space $\mathcal{X}$ to $\{0,1\}$, and $\epsilon > 0$, let $\mathcal{D}$ denotes the ...
- 29
7
votes
2
answers
477
views
Upper bound on VC-dimension of partitioned class
Fix $n,k\in \mathbb{N}_+$.
Let $\mathcal{H}$ be a set of functions from $\mathbb{R}^n$ to $\mathbb{R}$ with finite VC-dimension $d\in \mathbb{N}$. Let $\mathcal{H}_k$ denote the set of maps of the ...
- 364
4
votes
0
answers
154
views
Known relations between mutual information and covering number?
This is a question about statistical learning theory. Consider a hypothesis class $\mathcal{F}$, parameterized by real vectors $w \in \mathbb{R}^p$. Suppose I have a data distribution $D \sim \mu$ and ...
- 141
2
votes
1
answer
63
views
Non-linear transforms of RKHS question
I was reading the paper Norm Inequalities in Nonlinear Transforms (referenced in this question) but ran into difficulties, so I was wondering if anyone could help?
I think I follow the paper until I ...
- 41
57
votes
10
answers
10k
views
A clear map of mathematical approaches to Artificial Intelligence
I have recently become interested in Machine Learning and AI as a student of theoretical physics and mathematics, and have gone through some of the recommended resources dealing with statistical ...
1
vote
0
answers
85
views
Approximation of continuous function by multilayer Relu neural network
For continuous/holder function $f$ defined on a compact set K， a fix $L$ and $m_1,m_2,\dots,m_L$, can we find a multilayer Relu fully connected network g with depth $L$ and each $i$-th layer has width ...
- 781
1
vote
2
answers
221
views
Beating the $1/\sqrt n$ rate of uniform-convergence over a linear function class
Let $P$ be a probability distribution on $\mathbb R^d \times \mathbb R$, and let $(x_1,y_1), \ldots, (x_n,y_n)$ be an iid sample of size $n$ from $P$. Fix $\epsilon,t\gt 0$. For any unit-vector $w \in ...
- 6,853
0
votes
1
answer
103
views
Is it reasonable to consider the subgaussian property of the logarithm of the Gaussian pdf?
Let $Y$ denote a Gaussian random variable characterized by a mean $\mu$ and a variance $\sigma^2$. Consider $N$ independent and identically distributed (i.i.d.) copies of $Y$, denoted as $Y_1, Y_2, \...
- 287
2
votes
1
answer
92
views
VC-based risk bounds for classifiers on finite set
Let $X$ be a finite set and let $\emptyset\neq \mathcal{H}\subseteq \{ 0,1 \}^{\mathcal{X}}$. Let $\{(X_n,L_n)\}_{n=1}^N$ be i.i.d. random variables on $X\times \{0,1\}$ with law $\mathbb{P}$. ...
- 364
1
vote
1
answer
199
views
Rademacher complexity for a family of bounded, nondecreasing functions?
Let $\{\phi_k\}_{k=1}^K$ be a family of functions mapping from an interval $[a, b]$ to $[-1, 1]$.
That is, $\phi_k \colon[ a,b] \to [-1, 1]$ are nondecreasing maps on some finite interval $[a, b] \...
- 460
1
vote
0
answers
153
views
Distribution-free learning vs distribution-dependent learning
I came across some papers studying the problem of distribution-free learning, and I am interested in knowing the exact definition of distribution-free learning.
I have searched some literature:
In ...
- 11
4
votes
0
answers
121
views
Progress on "Un-Alching" ML?
So, a couple of years ago I watched both Ali Rahimi's NIPS speech "Machine Learning is Alchemy",
(where he talks about how the field lacks a solid, overarching, theoretical foundation) and ...
- 41
1
vote
1
answer
176
views
Tight upper-bounds for the Gaussian width of intersection of intersection of hyper-ellipsoid and unit-ball
Let $\Lambda$ be a positive-definite matrix of size $n$ and let $R \ge 0$, which may depend on $n$. Consider the set $S := \{x \in \mathbb R^n \mid \|x\|_2 \le R,\,\|x\|_{\Lambda^{-1}} \le 1\}$ where $...
- 6,853
1
vote
0
answers
24
views
Minimax statistical estimation of proximal transform $\mbox{prox}_g(\theta_0)$, from linear model data $y_i := x_i^\top \theta_0 + \epsilon_i$
tl;dr: My question pertains the subject of minimax estimation theory (mathematical statistics), in the context of linear regression.
Given a vector $\theta_0 \in \mathbb R^d$, consider the linear ...
- 6,853
2
votes
0
answers
292
views
Covering/Bracketing number of monotone functions on $\mathbb{R}$ with uniformly bounded derivatives
I am interested in the $\| \cdot \|_{\infty}$-norm bracketing number or covering number of some collection of distribution functions on $\mathbb{R}$.
Let $\mathcal{F}$ consist of all distribution ...
- 93
1
vote
0
answers
414
views
Conditions for equivalence of RKHS norm and $L^2(P)$ norm
Let $K$ be a psd kernel on an abstract space $X$ and let $H_K$ be the induced Reproducing Kernel Hilbert Space (RKHS). Let $P$ be a probability measure on $X$ such that $H_K \subseteq L^2(P_X)$ and ...
- 6,853
1
vote
1
answer
75
views
How far from a sparse parity function can a function be and still look like such a function on small sets?
Let $\mathbb F_2^n$ denote the set of binary vectors of length $n$. A $k$-sparse parity function is a linear function $h:\mathbb F_2^n\to\mathbb F_2$ of the form $h(x)=u\cdot x$ for some $u$ of ...
- 623
0
votes
0
answers
34
views
Normalizing a parameter in a regression
I am thinking about the possibility of making a parameter in my regression, let's say the $\lambda$ in a ridge regression, somehow, inside a range : $\lambda \in [0,1]$. Do you have any ideas how I ...
- 1
0
votes
0
answers
96
views
Verification of a certain computation of VC dimension
Disclaimer: I'm not very familiar with the concept of VC dimensions and how to manipulate such objects. I'd be grateful if expects on the subject (learning theory, probability), could kindly proof ...
- 6,853
1
vote
1
answer
230
views
VC dimension of a certain derived class of binary functions
Let $X$ be a measurable space and let $P$ be a probability distribution on $X \times \{\pm 1\}$. Let $F$ be a function class on $X$, i.e., a collection of (measurable) functions from $X$ to $\mathbb R$...
- 6,853
1
vote
1
answer
216
views
Rademacher complexity of function class $(x,y) \mapsto 1[|yf(x)-\alpha| \ge \beta]$ in terms of $\alpha$, $\beta$, and Rademacher complexity of $F$
Let $X$ be a measurable space and let $P$ be a probability distribution on $X \times \{\pm 1\}$. Let $F$ be a function class on $X$, i.e., a collection of (measurable) functions from $X$ to $\mathbb R$...
- 6,853
0
votes
0
answers
195
views
Upper-bound for bracketing number in terms of VC-dimension
Let $P$ be a probability distribution on a measurable space $\mathcal X$ (e.g;, some euclidean $\mathbb R^m$) and let $F$ be a class of funciton $f:\mathcal X \to \mathbb R$. Given, $f_1,f_2 \in F$, ...
- 6,853
1
vote
0
answers
99
views
$L_1$ convergence rates for multivariate kernel density estimation
Let $X$ be a random variable on $\mathbb R^d$ with probability density function $f$, and let $X_1,\ldots,X_n$ of $X$ be $n$ iid copies of $X$. Given a bandwidth parameter $h=h_n > 0$ and a kernel $...
- 6,853
4
votes
0
answers
164
views
Convergence rates for kernel empirical risk minimization, i.e empirical risk minimization (ERM) with kernel density estimation (KDE)
Let $\Theta$ be an open subset of some $\mathbb R^m$ and let $P$ be a probability distribution on $\mathbb R^d$ with density $f$ in a Sobolev space $W_p^s(\mathbb R^d)$, i.e all derivatives of $f$ ...
- 6,853
4
votes
2
answers
385
views
Bounds on the number of samples needed to learn a real valued function class
Let us see Theorem 6.8 in this book, https://www.cs.huji.ac.il/w~shais/UnderstandingMachineLearning/understanding-machine-learning-theory-algorithms.pdf
It gives us a lowerbound (and also an ...
- 617
1
vote
0
answers
63
views
Properties of a kernel convolution $K'(x,y) = \int_X\int_X K_0(x,a)K(a,b)K_0(b,y)d\mu(a)d\mu(b)$ where $K$ and $K_0$ are kernels on $(X,\mu)$
Let $(X,\mu)$ be a probability measure space and $K:X \times X \to \mathbb R$ be a (psd) kernel on $X$. Let $K_0$ be another kernel on $X$ and defined a new kernel $\widetilde K$ on $X$ by
$$
\...
- 6,853
2
votes
1
answer
157
views
Representer theorem for a loss / functional of the form $L(h) := \sum_{i=1}^n (|h(x_i)-y_i|+t\|h\|)^2$
Let $K:X \times X \to \mathbb R$ be a (positive-definite) kernel and let $H$ be the induced reproducing kernel Hilbert space (RKHS). Fix $(x_1,y_1),\ldots,(x_n,y_n) \in X \times \mathbb R$. For $t \ge ...
- 6,853
6
votes
1
answer
501
views
Why is this nonlinear transformation of an RKHS also an RKHS?
I came across this paper (beginning of page 6) where they stated that if $f,h\in \mathcal{H}$, where $\mathcal{H}$ is an RKHS, then $l_{h,f}=\left|f(x)-h(x)\right|^q$ where $q\geq 1$ also belongs to ...
- 383
3
votes
0
answers
461
views
Analytic formula for the eigenvalues of kernel integral operator induced by Laplace kernel $K(x,x') = e^{-c\|x-x'\|}$ on unit-sphere in $\mathbb R^d$
Let $d \ge 2$ be an integer and let $X=\mathcal S_{d-1}$ the unit-sphere in $\mathbb R^d$. Let $\tau_d$ be the uniform distribution on $X$. Define a function $K:X \times X \to \mathbb R$ by $K(x,y) := ...
- 6,853
1
vote
0
answers
233
views
Variance-based localized Rademacher complexity for RKHS unit-ball
Let $\mathscr X$ be a compact subset of $\mathbb R^d$ (e.g the unit-sphere). Let $K: \mathscr X \times \mathscr X \to \mathbb R$ be a positive kernel function and let $\mathscr H_K$ be the induced ...
- 6,853
0
votes
0
answers
340
views
Lower-bound on expected value of norm of transformation of random vector with iid Rademacher coordinates
Let $n$ be a large positive integer. Let $A$ be a positive-definite matrix such with eigenvalues $\lambda_1 \ge \lambda_2 \ge \ldots \ge \lambda_n$ such that $\lambda_n = o(1) \to 0$ and $\lambda_i=\...
- 6,853
1
vote
0
answers
96
views
Concentration for $\sum_{i=1}^n y_i \psi(x_i^\top u)$, for $y_1,\ldots,y_n \sim \{\pm 1\}$ and $x_1,\ldots,x_n$ uniform iid on hypersphere
Let $y_1,\ldots,y_n$ be drawn iid uniformly from $\{\pm 1\}$ and let $x_1,\ldots,x_n$ be drawn iid uniformly from the unit-sphere $(d-1)$-dimensional sphere $\mathbb S_{d-1}$, and independently from ...
- 6,853
3
votes
1
answer
311
views
Games and the right mathematical framework for GANs
Generative Adversarial Networks were introduced in http://papers.nips.cc/paper/5423-generative-adversarial-nets and has more than 20000 citations.
It is an important topic within deep learning.
Are ...
- 13.9k
1
vote
0
answers
99
views
Covering number after projection
In these lecture notes on Statistical Learning Theory we find the following definitions for covering numbers:
Definition. Let $(\mathcal{W}, d)$ be a metric space and $\mathcal{F} \subset \mathcal{W}$...
1
vote
1
answer
320
views
Finite VC dimension > the number of free parameters
I'm looking for an example of the following:
A hypothesis class $\mathcal{H}$ such that
$\forall h \in \mathcal{H}$, the number of free parameters of $h$ is equal to $n \in \mathbb{N}$ (where $n < ...
- 45
0
votes
1
answer
260
views
How large sample $m$ is enough [closed]
I have a $D$ probability distribution over $X =R^d$, i have two samples $s_1$ and $s_2$ from $D$, each having size $m_1$, $m_2$, a unit ball centered at origin $B(0)$, defined by $B(0)=\{x \in R^2: \|...
user166952
1
vote
1
answer
58
views
Fast rates in ERM: Extreme case of low-noise assumption implies non-differentiability
Some context: I am going through some literature on empirical risk minimization for bipartite ranking [1] that shows how certain "low-noise" conditions lead to fast rates of convergence of ...
- 111
8
votes
4
answers
2k
views
How to learn a continuous function?
Let $\Omega \subset \mathbb{R}^m$ be an open subset bounded with a smooth boundary.
Problem : Given any bounded continuous function $f:\Omega\to\mathbb{R}$, can we learn it to a given accuracy $\...
- 698
1
vote
1
answer
564
views
Upper bounding VC dimension of an indicator function class
I would like to upper bound the VC dimension of the function class $ F$ defined as follows:
$$ F := \left\{ (x,t) \mapsto \mathbb{1} \left( c_Q\min_{q \in Q} {\|x-q \|}_1 - t > 0 \right) \; | \; Q ...
- 11
11
votes
1
answer
898
views
Abstract mathematical concepts/tools appeared in machine learning research
I am interested in knowing about abstract mathematical concepts, tools or methods that have come up in theoretical machine learning. By "abstract" I mean something that is not immediately related to ...
0
votes
2
answers
297
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
2
votes
1
answer
753
views
Why we use Rademacher complexity for generalization error when we can have a trained function?
Let $G$ be a family of functions mapping from $Z$ to $[a, b]$ and $S=\left(z_{1}, \ldots, z_{m}\right)$ a fixed sample of size $m$ with elements in $Z$ . Then, the empirical Rademacher complexity of $...
- 53
24
votes
1
answer
4k
views
Relation between information geometry and geometric deep learning
Disclaimer: This is a cross-post from a very similar question on math.SE. I allowed myself to post it here after reading this meta
post about cross-posting between mathoverflow and math.SE, I did
...
- 343
6
votes
0
answers
120
views
Functional Equation of Zeta Function on Statistical Model
I've been studying [1] because I was interested in his ideas on the zeta function. I'll define it here (c.f. p. 31):
The Kullback-Leibler distance is defined as
$$
K(w)=\int q(x)f(x, w)dx\quad
f(x,w)...
- 429
0
votes
0
answers
156
views
Function classes with high Rademacher complexity
My question is two fold,
Is there any general understanding of what makes a function class have high Rademacher complexity? (Sudakov minoration would say that one sufficient condition for a class of ...
- 2,246