Podcast #128: We chat with Kent C Dodds about why he loves React and discuss what life was like in the dark days before Git. Listen now.

Questions tagged [lg.learning]

Machine learning and learning theory: PAC learning, algorithmic learning theory, and computational aspects of Bayesian inference and graphical models.

Filter by
Sorted by
Tagged with
0
votes
0answers
30 views

How do you prove the Nagarajan's Lemma? [on hold]

Let $H$ be a hypothesis class of multiclass predictors; namely, each $h\in H$ is a function from $X$ to $[k]$. Denote the Natarajan dimension of $H$ by $Ndim(H)$. Please prove the following lemma. $|...
4
votes
1answer
77 views

Terminology and references for a learning model

Let's say we're doing regression over $[0,1]^d$ -- either in the PAC sense with bounded-range agnostic noise or in the more classical-statistics sense with additive Gaussian noise. Suppose further ...
2
votes
1answer
64 views

Reconstruction of a sequence generated by a Markov chain - reference request

Let S be a finite sequence of symbols from a finite alphabet, with gaps - that is on some known locations an unknown number of symbols are missing. Assuming that the sequence , including the symbols ...
1
vote
0answers
46 views

Average smoothness learning rates

This question is somewhat related to this one. There are many results in statistics where convergence rates (including minimax ones) are given in terms of the smoothness properties of the underlying ...
0
votes
0answers
56 views

representation of concept classes and pac learning

I was reading the book of Kearns and Vazirani and I didn't completely understand the following: Let C be a concept class and suppose we want to PAC learn C, they say first consider a larger ...
1
vote
0answers
77 views

Agnostic query learning of decision trees

Gopalan, Kalai, Klivans gave an algorithm https://dl.acm.org/citation.cfm?id=1374376.1374451 for agnostically learning decision trees $h:\{0,1\}^n\to\{0,1\}$ under the uniform distribution given ...
3
votes
1answer
73 views

Agnostic query learning for DFAs

Angluin's membership+equivalence query algorithm allows to efficiently and exactly learn a target $n$-state DFA. But what if the target DFA is huge, or the target concept is not even a regular ...
0
votes
0answers
103 views

Lower bound to agnostic learning with membership queries

Setting: Let $X$ be a finite set and $C = \{0, 1\}^X$ a finite family of classifiers on $X$. Fix an $f \in \{0, 1\}^X$ not in $C$, a (possibly randomized and adaptive) learner $A$ has access to a ...
2
votes
1answer
92 views

References on generalization bounds

I'm looking for references (books, papers, lecture notes etc) on generalization bounds and their proofs. Specifically, I'm looking to fully understand the technique of defining a hypothesis class (or ...
2
votes
0answers
70 views

how is time complexity defined in computational learning theory

In general, when we say an algorithm $A$ PAC learns $C$ in time $t$, we say $A$ takes time $t$ before outputting a hypothesis $h$, and the hypothesis can be evaluated (on every $x$) in time $t$. Now ...
0
votes
1answer
133 views

Confusion about covering number

Problem I do not understand why larger $p$ will give a larger covering number. Since when $p\geq q$, the corresponding hypercube is also larger (by $\| x \| _ { q } \leq n ^ { ( 1 / q - 1 / p ) } \|...
1
vote
1answer
112 views

About learning a single Gaussian in total-variation distance

I am looking for the proof of this following result which I saw as being claimed as a "folklore" in a paper. It would be helpful if someone can share a reference where this has been shown! Let $G$ ...
0
votes
1answer
84 views

Lower bound of real valued bounded function

Is well known that the lower bound on number of example necessary to reach a given error for concept classes $\Omega(d/\varepsilon)$ (cf. also Agnostic PAC sampling lower bound ) I am looking for ...
2
votes
1answer
107 views

Oncina-Garcia RPNI algorithm for learning DFAs

The question refers to this paper: ftp://altea.dlsi.ua.es/people/oncina/articulos/asspr1992.pdf Given a sample of $p$ positive and $n$ negative strings, RPNI constructs a consistent DFA in time $O((p+...
1
vote
0answers
46 views

Back-propagation for computing derivative of certain line integral

Consider a function F (think of neural networks) with two sets of parameters: (1) model parameters $\mathbf{w}$, and (2) input data ${\bf x} \in {\mathbb R}^d$. Fix $i \in [d]$, consider the following ...
2
votes
1answer
125 views

Is there a gap between weak learning and PAC-learning?

For concreteness lets use the definitions of PAC and weak-learning as in the notes of Avrim Blum (http://www.cs.cmu.edu/~avrim/ML12/lect0208.txt) and also his notes on SQ-Learning (http://www.cs.cmu....
3
votes
0answers
99 views

Do features always induce a metric?

It is well-known in functional analysis that an inner product always induces a norm and a norm always induces a metric, and the reverse directions do not hold in general. I am wondering if a similar ...
7
votes
1answer
168 views

About assumptions needed to get convergence of stochastic gradient methods on non-convex objectives

What are the minimal conditions we know of under which we can prove that a stochastic gradient based algorithm can convergence to criticality on a non-convex objective? Are there any necessary ...
4
votes
1answer
84 views

What is the current state of the art in black-box grammar induction?

Grammar induction of Context Free Languages seems to be a very well researched field. I would like to know the current state of the art in inducing a Context Free Grammar (I am reading up Higuera's ...
2
votes
1answer
85 views

Empirical Rademacher averages versus Hoeffdings bound

Let $M$ be finite set with $n$ distinct elements. I want to probalistically approximate the relative counts $\frac{|P(Q)|}{|M|}$ of $Q \subseteq M$, where $P(Q) = |P \cap M|$. An upper-bound for ...
2
votes
0answers
71 views

Lower bounds for SRM?

This question is about structural risk minimization and model selection. Let $H_n$ be the collection of all binary classifiers on some fixed set with an $n$-bit description length in some fixed ...
1
vote
0answers
71 views

Average margin bounds for separable SVM

Suppose we're training a linear separator in the realizable PAC setting. Given $m$ labeled examples $(x_i,y_i)$ in $\mathbb R^d\times\{-1,1\}$, a (consistent) linear separator is a vector $w\in\mathbb ...
3
votes
2answers
189 views

How can AIC converge in the limit when even 2 parameter models can have infinite VC dimension?

AIC-based model-selection converges to zero error in the limit, and also has finite-sample convergence that is rate-optimal with respect to worst case minimax error [1]. (Note that AIC refers to ...
2
votes
1answer
64 views

On-policy/Off-policy Offline/Online Evaluation: Which would be an example of Online Off-Policy Evaluation?

In the context of the following question: off-policy and offline policy reinforcement learning , it can be concluded that off-policy/on-policy learning can be orthogonal to an online/offline sampling ...
5
votes
1answer
110 views

Is Bayes optimal RL of a finite set of DFAs feasible?

Let $Q$ be a finite set of states, $\Sigma$ a finite alphabet, $q_0\in Q$ the start state and $F\subseteq Q$ the set of accepting sets. Let $\{\delta_k:Q\times\Sigma\rightarrow Q\}_{k=1}^n$ be a set ...
3
votes
1answer
143 views

Rademacher complexity for piecewise-linear convex function

Consider a function family $$\ell(x)=\max_{1\leq k\leq K} a_k^\top x + b_k,$$ where $a_k,b_k \in \mathbb{R}^d$ are bounded in the sense of some norm and $K\geq 2$. What is the best upper bound on the ...
8
votes
1answer
483 views

Difficulty of “learning” rare instances

Is there any result showing that models (say SVM, Neural-Net, kNN, etc) will have difficulty in learning "rare" instances/tail phenomena?
4
votes
1answer
110 views

“Learning” when test and train distributions don't match

We know that the theory of PAC-learning is distribution-free, i.e. assuming that the test and train distributions are the same, we have guarantees on learning the hypothesis. Question: what if the ...
1
vote
0answers
61 views

Learnability of under some characteristics of the distribution

TLDR; is there any results showing that more concentrated (or easier) distributions are easier to learn? In PAC-learning, the guarantee is given for any underlying distributions. But in reality, we ...
1
vote
0answers
60 views

To what extent supervised learning ERM learn first-order knowledge

Suppose I have a collection of (hidden) first-order rules: $$ \mathcal{R}: \{ Q_i(x) => P_i(x) \}_{i=1}^{k} $$ all defined over $x \in \mathcal{X}$. I can use these rules and (automatically) ...
4
votes
2answers
361 views

Complexity of finding a consistent hyperplane

Given $m$ binary labeled points in $\mathbb{R}^d$, it is well-known that in general it's NP-hard to find a hyperplane that minimizes sample error. A brute-force search considers all $O(m^d)$ sample ...
3
votes
1answer
239 views

Rademacher complexity beyond the agnostic setting

The way I know of to bound generalization error by Rademacher complexity is Theorem 2.4 in this lecture notes, http://ttic.uchicago.edu/~tewari/lectures/lecture9.pdf. Here the quantity on the LHS that ...
4
votes
1answer
184 views

Tight VC bound for agnostic learning

The following result is supposedly known. However, the proofs I am able to find all prove a weaker result with an extra log factor. Where can I find the proof of the tight bound? Theorem. Let $\...
1
vote
0answers
76 views

Reference request for the relationship between approximating degree of Boolean functions and learning algorithms

This paper (http://www.cs.columbia.edu/~rocco/Public/stoc01.pdf) from STOC 2001 is possibly the first paper to show how to convert upperbounds on the $\frac{1}{3}-$approximation degree of a Boolean ...
10
votes
3answers
505 views

Proper PAC learning VC dimension bounds

It is well known that for a concept class $\mathcal{C}$ with VC dimension $d$, it suffices to obtain $O\left(\frac{d}{\varepsilon}\log\frac{1}{\varepsilon}\right)$ labelled examples to PAC learn $\...
0
votes
1answer
65 views

Learning a discrete distribution in $\ell_r$ norm

Let $P=(p_1,\ldots,p_d)$ be a distribution on $[d]$. Given $n$ iid draws from $P$, we construct some empirical estimate $\hat P_n=(\hat p_{n,1},\ldots,\hat p_{n,d})$. Let us define the $r$-risk by $$ ...
1
vote
1answer
167 views

$L_\mathcal{D}(A(S)) \le 0.1$ with prob at least $0.9$ implies PAC learnability

Suppose we have a hypothesis class $\mathcal{H}$ that is non-uniform learnable via sample compelxity function $m_{\text{NUL}}:[0,1]^2 \times \mathcal{H} \rightarrow \mathbb{N}$. If we define $\mathcal{...
2
votes
1answer
48 views

Nonsingular regret bound for UCB

Acer et al. "Finite-time Analysis of the Multiarmed Bandit Problem" show that the Upper Confidence Bound 1 (UCB1) algorithm has expected regret bounded by $$\left[ 8 \sum_{i: \mu_i < \mu^\ast} \...
1
vote
0answers
128 views

Cluster Assignment in the Stochastic Block Model

Recently, numerous papers have been published about the stochastic block model (SBM). In the literature about SBMs, a plethora of different settings are considered. I am interested in how vertices are ...
28
votes
1answer
1k views

Functions that are Not Efficiently Computable but Learnable

We know that (see, e.g., Theorems 1 and 3 of [1]), roughly speaking, under suitable conditions, functions that can be efficiently computed by Turing machine in polynomial time ("efficiently computable"...
2
votes
0answers
159 views

Oracle for Hamming distance to a secret bitvector

Let $s \in \{0,1\}^n$ be a secret bitvector. Define $f(x)$ to be the Hamming distance between $x$ and $s$. Suppose I am given an oracle for $f$, and I want to find $x$. How many queries to the ...
3
votes
2answers
414 views

Learning a coin's bias (localized)

It's well known that the minimax sample complexity for estimating the bias $p$ of a coin to additive error $\epsilon$ with confidence $\delta$ is $\Theta(\epsilon^{-2}\log(1/\delta))$. What if we ...
6
votes
2answers
496 views

Applications of Takens' theorem to TCS?

My apologies if the question is a tad vague—I did try to search the literature for more, but didn't find anything (the similarity between the keywords "Takens" and "taken" on Google may be partly to ...
3
votes
1answer
307 views

Rademacher complexity and lowerbounds in learning theory

Is there any function class known whose Rademacher complexity has a non-trivial lowerbound? Can the Rademacher complexity be used to lowerbound the generalization error in any learning situation?
5
votes
1answer
89 views

What is known about learning a maximal independent set in a (very) sparse graph?

Maximal independent set is known to be hard in many meanings (hard to approximate, $W[1]$-hard, etc.). But if the number of edges is very small, then the problem becomes simpler. Here, I'm interested ...
1
vote
0answers
128 views

Boolean functions with high query complexity for PAC learning

The most general theorem for PAC learning of Boolean functions that I am aware of is the theorem in section 3.4 of Ryan O'Donnel's book where its basically shown that Boolean functions whose Fourier ...
4
votes
0answers
1k views

Universal Approximation Theorem for non-sigmoidal activation functions

The most cited Universal Approximation Theories for multi-layer feedforward neural networks by Cybenko (1989) and Hornik (1991) assume the activation functions of the network to be sigmoidal. However, ...
3
votes
1answer
596 views

Examples of Fat-Shattering Dimension

What are some good examples for analysis of a class's Fat-Shattering dimension? By (Alon et al) I know that the Fat-Shattering Dimension characterizes the learnability of real-valued function classes ...
3
votes
1answer
121 views

Minimax agnostic risk for Lipschitz functions

For $L>0$, let $F_L$ be the class of all $L$-Lipschitz functions on $[0,1]$. Let $D$ be a joint distribution on $[0,1]\times\mathbb{R}$, from which we sample $n$ iid copies $(X_i,Y_i)$. Given any $...
4
votes
1answer
180 views

Kleinberg-consistency of spectral clustering

Spectral clustering refers to a family of graph-based algorithms, which usually rely on a similarity function rather than a metric, though a metric $\rho(x,y)$ can always be converted to a similarity ...