Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [lg.learning]

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

1
vote
0answers
67 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
67 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
99 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
0answers
66 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 ...
0
votes
1answer
77 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 ) } \|...
2
votes
0answers
68 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 ...
2
votes
1answer
54 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 ...
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"...
4
votes
1answer
816 views

VC dimension of intersection of half-spaces

Define $$l_i(x) := \text{sgn} \left( w_i^\top x - b_i \right)$$ for $i=1,...,n$, where $x \in \mathbb{R}^d$. Then define the classifier $$ g(x) := \max \{ l_1(x),..., l_n(x) \}$$ which represents ...
2
votes
1answer
367 views

Follow the Perturbed Leader for nonlinear cost functions

The famous FTPL algorithm [1] is analyzing linear cost function. Is there any generalized proof for nonlinear functions known? Note that in the last paragraph of [1] it says "It would be great to ...
6
votes
1answer
113 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 ...
0
votes
1answer
83 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 ...
1
vote
1answer
76 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 $G$ ...
2
votes
1answer
96 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
37 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
115 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
91 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 ...
4
votes
1answer
82 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
76 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
58 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 ...
10
votes
1answer
376 views

Agnostic PAC sampling lower bound

It is well-known that for classical PAC learning, $\Omega(d/\varepsilon)$ examples are necessary in order to acheive an error bound of $\varepsilon$ w.h.p., where $d$ is the VC-dimension of the ...
1
vote
0answers
55 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 ...
4
votes
2answers
349 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
2answers
181 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 ...
5
votes
1answer
105 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
126 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
481 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
108 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 ...
5
votes
0answers
246 views

What precisely is the extra power afforded by using deeper nets?

For any choice of activation function (fix the choice for all the hidden nodes for both the following DNNs) do we know of functions which some $k$ (hidden layer) DNN can compute but a $(k-1)-$DNN can'...
1
vote
0answers
57 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) ...
11
votes
1answer
493 views

Lower bounds for learning in the membership query and counterexample model

Dana Angluin (1987; pdf) defines a learning model with membership queries and theory queries (counterexamples to a proposed function). She shows that a regular language that is represented by a ...
3
votes
1answer
216 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
167 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 $\...
5
votes
2answers
369 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 $\...
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
332 views

Keyword selection problem in search engine marketing auction

First of all, I am still not sure whether cstheory is well adapted for this question, so I won't be offended if the crowd thinks it is not the case... In search engine marketing, several problems are ...
6
votes
1answer
9k views

Computational complexity of learning (classification) algorithms - fitting the parameters

My wish is to describe the time complexity of several classification approaches. For example, suppose we have $n$ data points in $m$ dimensional space and a binary class variable. We do not assume ...
41
votes
4answers
8k views

Is finding the minimum regular expression an NP-complete problem?

I am thinking of the following problem: I want to find a regular expression that matches a particular set of strings (for ex. valid email addresses) and doesn't match others (invalid email addresses). ...
20
votes
3answers
388 views

Property testing in other metrics?

There is a large literature on "property testing" -- the problem of making a small number of black box queries to a function $f\colon\{0,1\}^n \to R$ to distinguish between two cases: $f$ is a ...
0
votes
1answer
62 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 $$ ...
9
votes
1answer
285 views

VC dimension of Voronoi cells in R^d?

Suppose I have $k$ points in $\mathbb{R}^d$. These induce a Voronoi diagram. If I assign to each of the $k$ points a $\pm$ label, these induce a binary function on $\mathbb{R}^d$. Question: what is ...
1
vote
1answer
133 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{...
1
vote
0answers
124 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 ...
2
votes
1answer
47 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} \...
2
votes
0answers
143 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 ...
0
votes
1answer
553 views

Using Pearson Correlation Coefficient in computing user/item similarity

I'm researching for an algorithm for item-based/user-based collaborative filtering and I've come to this site. It uses Pearson correlation coefficient to compute similarity between users and when I ...
3
votes
2answers
406 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
1answer
360 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
249 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?