English
Related papers

Related papers: k-Step Relative Inductive Generalization

200 papers

A growing number of college applications has presented an annual challenge for college admissions in the United States. Admission offices have historically relied on standardized test scores to organize large applicant pools into viable…

Computers and Society · Computer Science 2023-05-24 Hansol Lee , René F. Kizilcec , Thorsten Joachims

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that…

Artificial Intelligence · Computer Science 2026-04-09 Qihan Ren , Peng Wang , Ruikun Cai , Shuai Shao , Dadi Guo , Yuejin Xie , Yafu Li , Quanshi Zhang , Xia Hu , Jing Shao , Dongrui Liu

The superior performance of deep learning relies heavily on a large collection of sample data, but the data insufficiency problem turns out to be relatively common in global electricity markets. How to prevent overfitting in this case…

Systems and Control · Electrical Eng. & Systems 2022-10-12 Guangchun Ruan , Jianxiao Wang , Haiwang Zhong , Qing Xia , Chongqing Kang

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry

Successor-style representations have many advantages for reinforcement learning: for example, they can help an agent generalize from past experience to new goals, and they have been proposed as explanations of behavioral and neural data…

Machine Learning · Computer Science 2021-03-17 Kianté Brantley , Soroush Mehri , Geoffrey J. Gordon

System identification, also known as learning forward models, transfer functions, system dynamics, etc., has a long tradition both in science and engineering in different fields. Particularly, it is a recurring theme in Reinforcement…

Implicit Neural Representation (INR) has emerged as an effective method for unsupervised image denoising. However, INR models are typically overparameterized; consequently, these models are prone to overfitting during learning, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2024-01-04 Zipei Yan , Zhengji Liu , Jizhou Li

The problem of matching two sets of multiple elements, namely set-to-set matching, has received a great deal of attention in recent years. In particular, it has been reported that good experimental results can be obtained by preparing a…

Machine Learning · Statistics 2023-02-28 Masanari Kimura

As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challenge is to aggregate a weighted combination of requirement…

Machine Learning · Computer Science 2026-01-07 Aneesh Barthakur , Luiz F. O. Chamon

We propose a new framework for discovering landmarks that automatically generalize across a domain. These generalized landmarks are learned from a set of solved instances and describe intermediate goals for planning problems where…

Artificial Intelligence · Computer Science 2025-09-01 Issa Hanou , Sebastijan Dumančić , Mathijs de Weerdt

Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited.…

Artificial Intelligence · Computer Science 2021-11-30 Hector Geffner

We introduce sequential analysis in quantum information processing, by focusing on the fundamental task of quantum hypothesis testing. In particular our goal is to discriminate between two arbitrary quantum states with a prescribed error…

Quantum entanglement lies at the heart in quantum information processing tasks. Although many criteria have been proposed, efficient and scalable methods to detect the entanglement of generally given quantum states are still not available…

Quantum Physics · Physics 2023-08-30 Lifeng Zhang , Zhihua Chen , Shao-Ming Fei

One-shot learning is proposed to make a pretrained classifier workable on a new dataset based on one labeled samples from each pattern. However, few of researchers consider whether the dataset itself supports one-shot learning. In this…

Machine Learning · Computer Science 2021-05-31 Hao Su

A generalized set theory (GST) is like a standard set theory but also can have non-set structured objects that can contain other structured objects including sets. This paper presents Isabelle/HOL support for GSTs, which are treated as type…

Logic in Computer Science · Computer Science 2022-07-26 Ciarán Dunne , J. B. Wells

In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit…

Computation and Language · Computer Science 2025-06-03 Junjie Zhang , Rushuai Yang , Shunyu Liu , Ting-En Lin , Fei Huang , Yi Chen , Yongbin Li , Dacheng Tao

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience with the outcomes achieved in that experience, and then imitate the relabeled experience. These outcome-conditioned imitation learning methods are…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Soumith Udatha , Sergey Levine , Ruslan Salakhutdinov

Hybrid learning methods use theoretical knowledge of a domain and a set of classified examples to develop a method for classification. Methods that use domain knowledge have been shown to perform better than inductive learners. However,…

Machine Learning · Computer Science 2011-01-26 Ridwan Al Iqbal

Most prior work on active learning of classifiers has focused on sequentially selecting one unlabeled example at a time to be labeled in order to reduce the overall labeling effort. In many scenarios, however, it is desirable to label an…

Machine Learning · Computer Science 2012-07-03 Javad Azimi , Alan Fern , Xiaoli Zhang-Fern , Glencora Borradaile , Brent Heeringa

Estimation of density functions supported on general domains arises when the data is naturally restricted to a proper subset of the real space. This problem is complicated by typically intractable normalizing constants. Score matching…

Methodology · Statistics 2020-09-25 Shiqing Yu , Mathias Drton , Ali Shojaie