English
Related papers

Related papers: How random are a learner's mistakes?

200 papers

It is well understood that if one is given a set $X \subset [0,1]$ of $n$ independent uniformly distributed random variables, then $$ \sup_{0 \leq x \leq 1} \left| \frac{\# X \cap [0,x]}{\# X} - x \right| \lesssim \frac{\sqrt{\log{n}}}{…

Probability · Mathematics 2025-01-24 Dmitriy Bilyk , Stefan Steinerberger

Let $(X_i)_{i=1,...,n}$ be a possibly nonstationary sequence such that $\mathscr{L}(X_i)=P_n$ if $i\leq n\theta$ and $\mathscr{L}(X_i)=Q_n$ if $i>n\theta$, where $0<\theta <1$ is the location of the change-point to be estimated. We…

Statistics Theory · Mathematics 2009-09-29 Samir Ben Hariz , Jonathan J. Wylie , Qiang Zhang

We explore the cycle types of a class of biased random derangements, described as a random game played by some children labeled $1,\cdots,n$. Children join the game one by one, in a random order, and randomly form some circles of size at…

Probability · Mathematics 2022-11-28 Poly H. da Silva , Arash Jamshidpey , Simon Tavaré

We consider the problem of estimating the mean of a normal distribution under the following constraint: the estimator can access only a single bit from each sample from this distribution. We study the squared error risk in this estimation…

Statistics Theory · Mathematics 2017-10-12 Alon Kipnis , John C. Duchi

Suppose that we observe $y \in \mathbb{R}^n$ and $X \in \mathbb{R}^{n \times m}$ in the following errors-in-variables model: \begin{eqnarray*} y & = & X_0 \beta^* +\epsilon \\ X & = & X_0 + W, \end{eqnarray*} where $X_0$ is an $n \times m$…

Machine Learning · Statistics 2017-04-04 Mark Rudelson , Shuheng Zhou

Traditional finance and macroeconomic models usually assume people can form rational expectations or reach them via a learning path by minimizing prediction errors. The recent Reference Model Based Learning (RMBL) model provides a new…

General Economics · Economics 2025-02-05 Jiaoying Pei

Let X, X_1,X_2,... be a sequence of i.i.d. random variables with mean $\mu=E X$. Let ${v_1^{(n)},...,v_n^{(n)}}_{n=1}^\infty$ be vectors of non-negative random variables (weights), independent of the data sequence…

Statistics Theory · Mathematics 2013-05-28 Miklos Csorgo , Yuliya Martsynyuk , Masoud Nasari

Consider a universal Turing machine that produces a partial or total function (or a binary stream), based on the answers to the binary queries that it makes during the computation. We study the probability that the machine will produce a…

Computational Complexity · Computer Science 2017-04-28 George Barmpalias , Douglas Cenzer , Christopher P. Porter

Consider an experiment involving a potentially small number of subjects. Some random variables are observed on each subject: a high-dimensional one called the "observed" random variable, and a one-dimensional one called the "outcome" random…

Machine Learning · Statistics 2018-06-15 Tarun Yellamraju , Mireille Boutin

Generation and prediction of time series is analyzed for the case of a Bit-Generator: a perceptron where in each time step the input units are shifted one bit to the right with the state of the leftmost input unit set equal to the output…

Condensed Matter · Physics 2016-08-31 E. Eisenstein , I. Kanter , D. A. Kessler , W. Kinzel

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an…

Machine Learning · Statistics 2017-11-21 Weiyang Liu , Bo Dai , Ahmad Humayun , Charlene Tay , Chen Yu , Linda B. Smith , James M. Rehg , Le Song

We study the problem, introduced by Qiao and Valiant, of learning from untrusted batches. Here, we assume $m$ users, all of whom have samples from some underlying distribution $p$ over $1, \ldots, n$. Each user sends a batch of $k$ i.i.d.…

Data Structures and Algorithms · Computer Science 2019-11-07 Sitan Chen , Jerry Li , Ankur Moitra

Most existing literature on supervised machine learning assumes that the training dataset is drawn from an i.i.d. sample. However, many real-world problems exhibit temporal dependence and strong correlations between the marginal…

Machine Learning · Statistics 2025-06-18 Nikola Sandrić

In their thought-provoking paper [1], Belkin et al. illustrate and discuss the shape of risk curves in the context of modern high-complexity learners. Given a fixed training sample size $n$, such curves show the risk of a learner as a…

Machine Learning · Computer Science 2022-06-08 Marco Loog , Tom Viering , Alexander Mey , Jesse H. Krijthe , David M. J. Tax

Small generalization errors of over-parameterized neural networks (NNs) can be partially explained by the frequency biasing phenomenon, where gradient-based algorithms minimize the low-frequency misfit before reducing the high-frequency…

Machine Learning · Computer Science 2022-09-27 Annan Yu , Yunan Yang , Alex Townsend

Empirical risk minimization is a standard principle for choosing algorithms in learning theory. In this paper we study the properties of empirical risk minimization for time series. The analysis is carried out in a general framework that…

Machine Learning · Statistics 2021-08-12 Christian Brownlees , Jordi Llorens-Terrazas

A matrix $M: A \times X \rightarrow \{-1,1\}$ corresponds to the following learning problem: An unknown element $x \in X$ is chosen uniformly at random. A learner tries to learn $x$ from a stream of samples, $(a_1, b_1), (a_2, b_2) \ldots$,…

Machine Learning · Computer Science 2017-08-10 Sumegha Garg , Ran Raz , Avishay Tal

Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not…

Infants, adults, non-human primates and non-primates all learn patterns implicitly, and they do so across modalities. The biological evidence supports the hypothesis that the mechanism for this learning is general but computationally local.…

Neurons and Cognition · Quantitative Biology 2021-08-16 John Rohrlich , Randall C. O'Reilly

Typical neural network trainings have substantial variance in test-set performance between repeated runs, impeding hyperparameter comparison and training reproducibility. In this work we present the following results towards understanding…

Machine Learning · Computer Science 2024-06-11 Keller Jordan