English
Related papers

Related papers: Rip van Winkle's Razor: A Simple Estimate of Overf…

200 papers

Artificial intelligence models trained from data can only be as good as the underlying data is. Biases in training data propagating through to the output of a machine learning model are a well-documented and well-understood phenomenon, but…

Machine Learning · Computer Science 2025-04-02 Stefan Rass , Martin Dallinger

Overfitting in linear regression is broken down into two main causes. First, the formula for the estimator includes 'forbidden knowledge' about training observations' residuals, and it loses this advantage when deployed out-of-sample.…

Methodology · Statistics 2022-09-27 Chris Rohlfs

Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to understanding this problem focus on statistical inference and generalization of individual analysis procedures. Yet the practice of data analysis…

Machine Learning · Computer Science 2015-09-28 Cynthia Dwork , Vitaly Feldman , Moritz Hardt , Toniann Pitassi , Omer Reingold , Aaron Roth

When multiple investigators analyze a common dataset, the data reuse induces dependence across testing procedures, affecting the distribution of errors. Existing techniques of managing dependent tests require either cross-study coordination…

Statistics Theory · Mathematics 2026-04-10 Reid Dale , Jordan Rodu , Maria E. Currie , Mike Baiocchi

Excessive reuse of test data has become commonplace in today's machine learning workflows. Popular benchmarks, competitions, industrial scale tuning, among other applications, all involve test data reuse beyond guidance by statistical…

Machine Learning · Computer Science 2019-05-30 Horia Mania , John Miller , Ludwig Schmidt , Moritz Hardt , Benjamin Recht

The phenomenon of benign overfitting, where a predictor perfectly fits noisy training data while attaining near-optimal expected loss, has received much attention in recent years, but still remains not fully understood beyond well-specified…

Machine Learning · Computer Science 2023-04-18 Ohad Shamir

The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is overfitted to a test set is challenging as independent test…

Machine Learning · Computer Science 2019-11-15 Roman Werpachowski , András György , Csaba Szepesvári

Model selection on validation data is an essential step in machine learning. While the mixing of data between training and validation is considered taboo, practitioners often violate it to increase performance. Here, we offer a simple,…

Machine Learning · Statistics 2018-02-19 Guy Tennenholtz , Tom Zahavy , Shie Mannor

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

Benign overfitting is a phenomenon in machine learning where a model perfectly fits (interpolates) the training data, including noisy examples, yet still generalizes well to unseen data. Understanding this phenomenon has attracted…

Machine Learning · Computer Science 2025-05-20 Junhyung Park , Patrick Bloebaum , Shiva Prasad Kasiviswanathan

In statistical learning, a dataset is often partitioned into two parts: the training set and the holdout (i.e., testing) set. For instance, the training set is used to learn a predictor, and then the holdout set is used for estimating the…

Machine Learning · Computer Science 2019-11-05 Jun Zhao

In our era of enormous neural networks, empirical progress has been driven by the philosophy that more is better. Recent deep learning practice has found repeatedly that larger model size, more data, and more computation (resulting in lower…

Machine Learning · Computer Science 2024-05-17 James B. Simon , Dhruva Karkada , Nikhil Ghosh , Mikhail Belkin

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data.…

Machine Learning · Computer Science 2021-11-09 Saurabh Garg , Sivaraman Balakrishnan , J. Zico Kolter , Zachary C. Lipton

Information-directed sampling (IDS) has revealed its potential as a data-efficient algorithm for reinforcement learning (RL). However, theoretical understanding of IDS for Markov Decision Processes (MDPs) is still limited. We develop novel…

Machine Learning · Computer Science 2022-11-28 Botao Hao , Tor Lattimore

Excessive reuse of holdout data can lead to overfitting. However, there is little concrete evidence of significant overfitting due to holdout reuse in popular multiclass benchmarks today. Known results show that, in the worst-case,…

Machine Learning · Computer Science 2019-05-27 Vitaly Feldman , Roy Frostig , Moritz Hardt

This work considers the problem of binary classification: given training data $x_1, \dots, x_n$ from a certain population, together with associated labels $y_1,\dots, y_n \in \left\{0,1 \right\}$, determine the best label for an element $x$…

Statistics Theory · Mathematics 2016-07-04 Nicolas Garcia Trillos , Ryan Murray

Classification rules can be severely affected by the presence of disturbing observations in the training sample. Looking for an optimal classifier with such data may lead to unnecessarily complex rules. So, simpler effective classification…

Statistics Theory · Mathematics 2017-01-19 Marina Antolín , Eustasio Del Barrio , Jean-Michel Loubes

The study of adaptive data analysis examines how many statistical queries can be answered accurately using a fixed dataset while avoiding false discoveries (statistically inaccurate answers). In this paper, we tackle a question that…

Machine Learning · Computer Science 2023-02-09 Roi Livni

A central issue of many statistical learning problems is to select an appropriate model from a set of candidate models. Large models tend to inflate the variance (or overfitting), while small models tend to cause biases (or underfitting)…

Statistics Theory · Mathematics 2020-12-25 Jie Ding , Enmao Diao , Jiawei Zhou , Vahid Tarokh

We consider a hypothesis testing problem where a part of data cannot be observed. Our helper observes the missed data and can send us a limited amount of information about them. What kind of this limited information will allow us to make…

Information Theory · Computer Science 2020-09-08 Marat V. Burnashev
‹ Prev 1 2 3 10 Next ›