English
Related papers

Related papers: Aggregated Hold-Out

200 papers

If the trend of learned components eventually outperforming their hand-crafted version continues, learned optimizers will eventually outperform hand-crafted optimizers like SGD or Adam. Even if learned optimizers (L2Os) eventually outpace…

Machine Learning · Computer Science 2022-09-20 Isabeau Prémont-Schwarz , Jaroslav Vítků , Jan Feyereisl

The kick-one-out (KOO) method is a variable selection method based on a model selection criterion. The method is very simple, and yet it has consistency in variable selection under a high-dimensional asymptotic framework with a specific…

Methodology · Statistics 2025-09-16 M. Ohishi , R. Oda

Adaptive data analysis has posed a challenge to science due to its ability to generate false hypotheses on moderately large data sets. In general, with non-adaptive data analyses (where queries to the data are generated without being…

Methodology · Statistics 2018-09-18 Preetum Nakkiran , Jarosław Błasiok

Exploration is essential in modern learning, from reinforcement learning environments with small neural policies to large language models (LLMs). Existing work, such as DPO, leverages full sequence log-likelihoods to capture an entire…

Machine Learning · Computer Science 2025-08-27 Gaurish Trivedi , Alakh Sharma , Kartikey Singh Bhandari , Dhruv Kumar , Pratik Narang , Jagat Sesh Challa

Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout budget is small,…

Machine Learning · Computer Science 2026-02-02 Youngeun Kim

We consider the parametric learning problem, where the objective of the learner is determined by a parametric loss function. Employing empirical risk minimization with possibly regularization, the inferred parameter vector will be biased…

Machine Learning · Statistics 2017-11-16 Ahmad Beirami , Meisam Razaviyayn , Shahin Shahrampour , Vahid Tarokh

In this paper, a new approach to computing the generalisation performance is presented that assumes the distribution of risks, $\rho(r)$, for a learning scenario is known. From this, the expected error of a learning machine using empirical…

Machine Learning · Computer Science 2020-03-27 Antonia Marcu , Adam Prügel-Bennett

The goal of online prediction with expert advice is to find a decision strategy which will perform almost as well as the best expert in a given pool of experts, on any sequence of outcomes. This problem has been widely studied and…

Machine Learning · Computer Science 2018-05-22 Parameswaran Kamalaruban , Robert C. Williamson , Xinhua Zhang

We consider the selection of prediction models for Markovian time series. For this purpose, we study the theoretical properties of the hold-out method. In the econometrics literature, the hold-out method is called out-of-sample and is the…

Statistics Theory · Mathematics 2022-04-13 Remy Garnier , Raphaël Langhendries , Joseph Rynkiewicz

We compare and contrast two approaches to validating a trained classifier while using all in-sample data for training. One is simultaneous validation over an organized set of hypotheses (SVOOSH), the well-known method that began with VC…

Machine Learning · Statistics 2015-10-12 Eric Bax , Ya Le

In this work, we introduce the {\em average top-$k$} (\atk) loss as a new aggregate loss for supervised learning, which is the average over the $k$ largest individual losses over a training dataset. We show that the \atk loss is a natural…

Machine Learning · Statistics 2017-12-21 Yanbo Fan , Siwei Lyu , Yiming Ying , Bao-Gang Hu

While Group Relative Policy Optimization (GRPO) has emerged as a scalable framework for critic-free policy learning, extending it to settings with explicit behavioral constraints remains underexplored. We introduce Constrained GRPO, a…

Machine Learning · Computer Science 2026-02-09 Roger Girgis , Rodrigue de Schaetzen , Luke Rowe , Azalée Robitaille , Christopher Pal , Liam Paull

Regression uses supervised machine learning to find a model that combines several independent variables to predict a dependent variable based on ground truth (labeled) data, i.e., tuples of independent and dependent variables (labels).…

Machine Learning · Computer Science 2021-10-29 Maria Ulan , Welf Löwe , Morgan Ericsson , Anna Wingkvist

Momentum is a simple and widely used trick which allows gradient-based optimizers to pick up speed along low curvature directions. Its performance depends crucially on a damping coefficient $\beta$. Large $\beta$ values can potentially…

Machine Learning · Computer Science 2019-05-02 James Lucas , Shengyang Sun , Richard Zemel , Roger Grosse

The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion…

Machine Learning · Statistics 2016-08-24 Alain Celisse , Benjamin Guedj

RLVR has enhanced the reasoning capabilities of Large Language Models (LLMs) across various tasks. However, GRPO, a representative RLVR algorithm, suffers from a critical limitation: when all responses within a group are either entirely…

Machine Learning · Computer Science 2025-09-24 Gongrui Nan , Siye Chen , Jing Huang , Mengyu Lu , Dexun Wang , Chunmei Xie , Weiqi Xiong , Xianzhou Zeng , Qixuan Zhou , Yadong Li , Xingzhong Xu

Federated Learning has been recently proposed for distributed model training at the edge. The principle of this approach is to aggregate models learned on distributed clients to obtain a new more general "average" model (FedAvg). The…

Machine Learning · Statistics 2022-07-20 Adnan Ben Mansour , Gaia Carenini , Alexandre Duplessis , David Naccache

We propose a new method for estimating the number of answers OUT of a small join query Q in a large database D, and for uniform sampling over joins. Our method is the first to satisfy all the following statements. - Support arbitrary Q,…

Databases · Computer Science 2023-04-11 Kyoungmin Kim , Jaehyun Ha , George Fletcher , Wook-Shin Han

Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards, but its group-mean-centered advantage can fail under binary rewards. The failure mode is gradient starvation: when every…

Machine Learning · Computer Science 2026-05-11 Wenhua Nie , Jianan Wu , Junlin Liu , Ziwei Li , Zheng Lin , Zhang Zijian , Yilong Fan , Haoran Zheng , Jyh-Shing Roger Jang

In conventional supervised classification, true labels are required for individual instances. However, it could be prohibitive to collect the true labels for individual instances, due to privacy concerns or unaffordable annotation costs.…

Machine Learning · Computer Science 2023-06-29 Zixi Wei , Lei Feng , Bo Han , Tongliang Liu , Gang Niu , Xiaofeng Zhu , Heng Tao Shen