Questions tagged [learning-theory]

Questions about the design and analysis of machine learning algorithms.

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

What does “smooth control” here mean?

I came across the following statement in this pdf. This allows the learner to have smooth control over the bias-complexity tradeoff. What does "smooth control" here mean? How do you understand ...
1
vote
1answer
25 views

What are the basics of CS i should know,before I start my journey into machine learning

I am myself a non-cs graduate and would love to be a machine learning engineer. I have learned to code and know the basics of <...
0
votes
0answers
15 views

How do you interpret this learning curve? [closed]

Loss is MSE; orange is validation loss, blue training loss. The task is NN regression (18 inputs, 2 outputs), one layer 300 hidden units. Tuning the lr, mom, l2 regularization parameters this is the ...
0
votes
1answer
36 views

VC dimension of the class of polynomial classifiers of degree $n$

I came across this statement on page 85 of the book "understanding machine learning: from theory to algorithms" The general idea is as follows: Consider a binary classification problem with the ...
1
vote
0answers
18 views

How can I understand the multi-class version of “shattering” intuitively? [closed]

I'm learning machine learning. VC dimension is a good way to measure the complexity of hypothesis class for binary classifier and has a very good intuitive explanation from shattering. When we ...
1
vote
0answers
20 views

Covering numbers to show that H is agnostically PAC-learnable

Suppose $X=[0,1]$ and $Y=[0,1]$, and we use the squared loss Let's define the hypothesis class $H = {h(x) = (x-a)^2 : a \in [0,1]}$. Question: How can covering numbers be used to show that this ...
-1
votes
1answer
39 views

How do you prove the Natarajan's Lemma intuitively?

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 $Ndim(H)$. Hope you can give me an intuitive ...
1
vote
0answers
14 views

Hypothesis space in AdaBoost or general Machine learning

I was curious about the following: in most learning algorithms, when an algorithm is said to learn a concept class $C$ then the algorithm outputs a function from the hypothesis space $H$ and often ...
1
vote
1answer
46 views

How can the VC-dimension of Turing machine be finite?

The VC-dimension of a hypothesis class $\mathcal{H}$ is defined to be the size of the maximal set $C$ such that $\mathcal{H}$ cannot shutter. This paper shows that the VC-dimension of the set of all ...
0
votes
1answer
69 views

Dana Angluin's L* algorithm - Hypothesis inconsistent

is it possible for the Dana Angluin's L* algorithm that a hypothesis is inconsistent? So assume we have a closded observation table for a regular language L. Now after creating the hypothesis we will ...
0
votes
0answers
39 views

Why is Agnostic PAC learnability a stronger criterion as compared to the PAC learnability?

I am trying to understand the mentioned question. According to me, it should be other way around as it is easier to find hypothesis which is approximately correct compared to the optimal hypothesis in ...
0
votes
1answer
46 views

Weighting function for Non Uniform Learning

Consider a hypothesis class $H = \cup_{n=1}^{\infty} H_n$, where for every $n\in N$, $H_n$ is finite. Find a weighting function $w : H ->[0, 1]$ such that $\sum_{h \in H} w(h) ≤ 1$ and so that for ...
1
vote
1answer
24 views

what does this phrase mean: “train a policy network”

I am familiar with the basics (and perhaps a substantial amount of basics) of imitation learning and reinforcement learning. In IL (imitation), we take demonstrations from an assumed expert, which we ...
0
votes
0answers
12 views

OR functions and SQ-Learning

Anyone can describe or give a reference which has a clear description and detailed proof of the SQ-Learning algorithm for the OR class of Boolean functions?
2
votes
0answers
29 views

Query complexity of exact learning and combinatorial parameter

When defining the query complexity of exact learning for a concept $c$ (considered as a function from $\{0,1\}^n \mapsto \{0,1\}$) in a concept class $\mathcal{C}$, we often come across the following ...
1
vote
0answers
40 views

What are good examples of computational theories for A.I. according to David Marr's Definition?

I was reading David Marr's "Artificial Intelligence-A Personal View" and he talks about "computational theory of AI" or what he laters labels as "Type 1" Theory. He provides the example of Chomsky's ...
1
vote
1answer
238 views

VC dimension of finite unions of one-sided intervals

What is the VC dimension of $k$ finite unions of one-sided intervals: If we take 3 one-sided intervals like $(-\infty, a_1] $, $(-\infty, a_2] $ and $(-\infty, a_3] $, I think union of these ...
1
vote
1answer
35 views

Does selecting the same arm has the same reward?

In multi-armed bandit problem, we have a set of $K$ arms. In each round $t$, a bandit selects an arm $k$ and receives a reward $r_{kt}$. The objective is to maximize the rewards after $T$ rounds. My ...
2
votes
0answers
52 views

Automatic learning/discovery of logics

Are there efforts to automatically discover new logics? Logics are simple structures - they have formal language, deduction rules, semantics and certain properties that are proved or discarded for ...
5
votes
1answer
101 views

VC dimensions: Let ${x_1, \ldots, x_N}$ be $N$ labelled points on $\mathbb{R}$, then there exists a sinusoid that separates these points

(Proposition, pg 26): Let ${x_1, \ldots, x_N}$ be $N$ points on $\mathbb{R}$, $N \in \mathbb{Z}$, labelled either $+1$ or $-1$ , then there exists a function from the set $\{t \mapsto \sin(\omega t)| \...
1
vote
1answer
228 views

Geometric intuition behind VC-dimension

Recently, I learnt about VC-dimension and how its boundedness assures PAC learnability on uncountable range spaces (let's assume that hypothesis class is the same as the family of concepts we want to ...
2
votes
1answer
31 views

Neural Network | What is the purpose of hidden layers and how many should I use?

I am pretty new to Neural Networks and I have two questions about hidden layers: 1. What is the purpose of hidden layers? I was wondering this because obviously you can get every result you want with ...
1
vote
0answers
124 views

Learning curve for model selection [closed]

I'm a newbie in machine learning field. And I need to choose the best model for my classification model, so i use "learning curve" from sk-learn to make selection. I train and plot learning curve on ...
1
vote
1answer
40 views

What does it mean the norm symbol applied to a concept?

I'm reading this paper: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.14 or http://www.jmlr.org/papers/volume10/kontorovich09a/kontorovich09a.pdf On page 1101 are introduced 2 functions ...
2
votes
1answer
2k views

Is it true that PAC is a subset of agnostic PAC?

I would like to see the proof or a refernce to it. I feel it is obvious but my tutor insists the other way (agnostic PAC is a subset of PAC, and there are problems in PAC that are not angostic PAC).
2
votes
0answers
257 views

Faster RCNN: how to translate coordinates

I'm trying to understand and use the Faster R-CNN algorithm on my own data. My question is about ROI coordinates: what we have as labels, and what we want in the end, are ROI coordinates in the input ...
7
votes
0answers
2k views

Detecting the damaged regions in cars

Detecting the regions where a car has been damaged and the extent to which it has been damaged is a very interesting problem. It has potential applications in automatic auto insurance claims. ...
0
votes
0answers
39 views

Is feasible learning using just one algorithm and just one class of functions?

Suppose that in an enterprise there is a section specialized in data prediction problems, and to make easier the software maintainance, the next decision is taken: it will be used only one algorithm ...
2
votes
1answer
219 views

Random forests on monotone training set yields a monotone classifier?

Suppose I train a random forests classifier on a monotone training set. Is the resulting classifier guaranteed to be a monotone function? Suppose I apply the ID3 algorithm (the greedy algorithm) to ...
3
votes
1answer
70 views

Supervised learning with no prior information

I am now reading two modern books on machine learning theory. Both of them emphasize that, in order to succeed in supervised learning, one must choose a good hypothesis class. "Good" means that it is ...
4
votes
0answers
54 views

VC dimension and binary operations

There are two classes of binary functions, $F_1,F_2$. The VC-dimension of $F_i$ is $d_i$. Is there any simple formula for the VC-dimension of the following classes? $F_\lor := \{ f_1(x) \lor f_2(x) |...
6
votes
2answers
303 views

any hope for a universal automatic parser?

Say you are a program, and you are given some source code but you don't know in what language, it can be C++/Java/Python/Lisp/... all you know is that it is highly structured and LR(1) parse-able, and ...
3
votes
1answer
382 views

The VC dimension when the samples are fixed

The VC dimension is usually used in the following way. There is a space of hypotheses. There is an unknown probability distribution. We sample some training-samples from this distribution. We find the ...
1
vote
1answer
59 views

In the learning theory version of Occam's razor, why can't I just declare whatever hypothesis I want to be “shortest”?

Occam's razor states that shorter explanations (formally speaking, hypotheses) are more likely to be correct. Indeed this can be formalized: for a hypothesis class $\mathcal H$ one may ascribe ...
1
vote
0answers
115 views

Is SRM necessary to prove that a countable union of agnostic PAC learnable classes is nonuniformly learnable?

The following I believe is a direct proof of this fact. If a learner is tasked to be $\epsilon$-competitive with a hypothesis $h \in \mathcal H_n$, where $\mathcal H_n$ is agnostic PAC learnable, it ...
0
votes
0answers
43 views

Is there a non-linear version of ICA?

"Independent Component Analysis" is this : someone is sampling a random vector $s \in \mathbb{R}^d$ such that all its components $s_i$ are mutually independent and $\mathbb{E}[s_i^4] < 3$ and the ...
1
vote
0answers
122 views

Why is it NP-hard to learn a disjunction of k variables as a disjunction of fewer than k log n variables?

I'm looking at the claim in An algorithmic theory of learning: Robust concepts and random projection by R. I. Arriaga and S. Vempala (2006): Further, it is NP-hard to learn a disjunction of k ...
0
votes
1answer
291 views

VC dimension of monotone disjunctions of length k over n variables?

There are of course $n \choose k$ monotone disjunctions which bounds the VC dimension at $\log_2 {n \choose k}$. I'm wondering if this is bound at $k \log_2 n$? (Possibly follows from combinatorial ...
2
votes
1answer
916 views

single agent vs multiple agent reinforcement learning

I am confused about 'single' vs 'multiple' agent reinforcement learning. Let's say that I have 1 hunter who I am training to hunt 1 static prey, so that only the hunter is moving around. This is ...
3
votes
1answer
31 views

Learning a small disjunction using an input distribution of our choice

I have a boolean function $f: \{0,1\}^n \to \{0,1\}$ that I know takes the form $$f(x_1,\dots,x_n) = x_{i_1} \lor x_{i_2} \lor \dots \lor x_{i_k}.$$ I don't know the values of $i_1,\dots,i_k$, but I ...
2
votes
1answer
95 views

Learning a small disjunction

I have a boolean function $f: \{0,1\}^n \to \{0,1\}$ that I know takes the form $$f(x_1,\dots,x_n) = x_{i_1} \lor x_{i_2} \lor \dots \lor x_{i_k},$$ but I don't know the values of $i_1,\dots,i_k$. ...
0
votes
1answer
101 views

A clarification on the taxonomy of Evolutionary Algorithms

A rather basic question but I am confused about the characterization of a certain local search method which I want to describe in the framework of EAs. In particular, consider an EA which in every ...
7
votes
2answers
929 views

PAC learning axis parallel rectangles

I am trying to understand the proof that the axis parallel rectangles are PAC learnable in the realizable case. This means that given $\epsilon, \delta$ with enough data we can find a function $h$ ...
0
votes
1answer
874 views

How do I continue learning programming, beyond the basics? [closed]

DISCLAIMER: I understand that I might not be posting in the right part of StackExchange, or this question might have been asked before (I haven't found it). If this offends anybody, I apologize. I'm ...
1
vote
0answers
148 views

Sample Complexity for Real-Valued PAC-Learnable Functions

Can anyone shed some light on how the VC Dimension affects the sample complexity bounds of infinite hypothesis classes with real-valued outputs in PAC learning, or how to calculate the sample ...
4
votes
1answer
2k views

How to implement the regret matching algorithm?

My question is the following: How to calculate the regret in practice? I am trying to implement the regret matching algorithm but I do not understand how to do it. First, I have $n$ players with the ...
-1
votes
1answer
379 views

Training Error & Convergence to True Error

I Take some online class for Machine Learning. one of teacher say this sentence. if we have m data points, the training error converges to the true error as m → ∞. i thought, this sentence not ...
1
vote
3answers
596 views

Over-fitting Always Occurs?

i get stuck in one sentence in machine learning. i read tom Mitchel book on ML, and some other materials. if we have small training set, always over-fit can occurs? or is likely to occurs? i read ...
-1
votes
1answer
64 views

Policy function π in Reinforcement learning unclear

I have one question about policy function in Reinforcement learning. in fact this function indicates which action should be done in each state? Or this function indicate for get the ...
1
vote
0answers
107 views

If one hypothesis class is a proper subset of another, what is the relation of their VC dimensions?

Assume two hypotheses classes $H_A\subset H_B$ defined over the same instance space $\delta$. Assume also $VC(H_A)=d$, does this mean $VC(H_B)\geq d$ ? where $VC$ is the VC dimension. We can use the ...