paper-with-me

Papers Learning Theory

“Learning Theory” 태그가 달린 논문 852편 · 필터 해제

On the Hardness of Bandit Learning

2025-06-17 · Nataly Brukhim, Aldo Pacchiano, Miroslav Dudik, Robert Schapire

We study the task of bandit learning, also known as best-arm identification, under the assumption that the true reward function f belongs to a known, but arbitrary, function class F. We seek a general theory of bandit le…

Learning Theory

Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach

2025-06-16 · Shreyas Rajeev, B Sathish Babu

Kernel size selection in Convolutional Neural Networks (CNNs) is a critical but often overlooked design decision that affects receptive field, feature extraction, computational cost, and model accuracy. This paper propos…

Computational Efficiencyimage-classificationImage ClassificationLearning Theory+3

The Universality Lens: Why Even Highly Over-Parametrized Models Learn Well

2025-06-09 · Meir Feder, Ruediger Urbanke, Yaniv Fogel

A fundamental question in modern machine learning is why large, over-parameterized models, such as deep neural networks and transformers, tend to generalize well, even when their number of parameters far exceeds the numb…

Ensemble LearningLearning Theory

Learning Theory of Decentralized Robust Kernel-Based Learning Algorithm

2025-06-05 · Zhan Yu

We propose a new decentralized robust kernel-based learning algorithm within the framework of reproducing kernel Hilbert space (RKHS) by utilizing a networked system that can be represented as a connected graph. The robu…

Learning Theory

What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness

2025-06-04 · Yang Cai, Alkis Kalavasis, Katerina Mamali, Anay Mehrotra 외

Most of the widely used estimators of the average treatment effect (ATE) in causal inference rely on the assumptions of unconfoundedness and overlap. Unconfoundedness requires that the observed covariates account for all…

Causal InferenceLearning Theory

A Machine Learning Theory Perspective on Strategic Litigation

2025-06-03 · Melissa Dutz, Han Shao, Avrim Blum, Aloni Cohen

Strategic litigation involves bringing a legal case to court with the goal of having a broader impact beyond resolving the case itself: for example, creating precedent which will influence future rulings. In this paper, …

Learning Theory

Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks

2025-06-02 · Taisuke Kobayashi, Shingo Murata

This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, noise and dropout on the internal state o…

Imitation LearningLearning TheoryVariational Inference

Learning DNF through Generalized Fourier Representations

2025-06-01 · Mohsen Heidari, Roni Khardon

The Fourier representation for the uniform distribution over the Boolean cube has found numerous applications in algorithms and complexity analysis. Notably, in learning theory, learnability of Disjunctive Normal Form (D…

Learning Theory

Distribution free M-estimation

2025-05-28 · Felipe Areces, John C. Duchi

The basic question of delineating those statistical problems that are solvable without making any assumptions on the underlying data distribution has long animated statistics and learning theory. This paper characterizes…

Learning TheoryStochastic Optimization

Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate

2025-05-27 · Shiwei Zeng, Jie Shen

Attribute-efficient learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevalent data corruptions or even adversarial atta…

AttributeLearning TheoryPAC learning

A Semantic Change Detection Network Based on Boundary Detection and Task Interaction for High-Resolution Remote Sensing Images

2025-05-26 · IEEE Transactions on Neural Networks and Learning Systems 2025 5 · Yingjie Tang; Shou Feng; Chunhui Zhao; Yongqi Chen; Zhiyong Lv; Weiwei Sun

Semantic change detection (CD) not only helps pinpoint the locations where changes occur, but also identifies the specific types of changes in land cover and land use. Currently, the mainstream approach for semantic CD (…

Boundary DetectionChange DetectionChange detection for remote sensing imagesLearning Theory+1

Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems

2025-05-24 · Giacomo Turri, Luigi Bonati, Kai Zhu, Massimiliano Pontil 외

We introduce an encoder-only approach to learn the evolution operators of large-scale non-linear dynamical systems, such as those describing complex natural phenomena. Evolution operators are particularly well-suited for…

Learning TheoryOperator learningRepresentation Learning

Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review

2025-05-22 · Beyazit Bestami Yuksel, Ayse Yilmazer Metin

This paper presents a comprehensive synthesis of major breakthroughs in artificial intelligence (AI) over the past fifteen years, integrating historical, theoretical, and technological perspectives. It identifies key inf…

Federated LearningGPULearning TheorySynthetic Data Generation

An Asymptotic Equation Linking WAIC and WBIC in Singular Models

2025-05-20 · Naoki Hayashi, Takuro Kutsuna, Sawa Takamuku

In statistical learning, models are classified as regular or singular depending on whether the mapping from parameters to probability distributions is injective. Most models with hierarchical structures or latent variabl…

Computational EfficiencyLearning TheoryModel Selection

Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping

2025-05-19 · Jianfeng Xu

[Objective] This study focuses on addressing the current lack of a unified formal theoretical framework in machine learning, as well as the deficiencies in interpretability and ethical safety assurance. [Methods] A forma…

Learning Theory

Learning Guarantee of Reward Modeling Using Deep Neural Networks

2025-05-10 · Yuanhang Luo, Yeheng Ge, Ruijian Han, Guohao Shen

In this work, we study the learning theory of reward modeling with pairwise comparison data using deep neural networks. We establish a novel non-asymptotic regret bound for deep reward estimators in a non-parametric sett…

Learning Theory

New Statistical and Computational Results for Learning Junta Distributions

2025-05-09 · Lorenzo Beretta

We study the problem of learning junta distributions on $\{0, 1\}^n$, where a distribution is a $k$-junta if its probability mass function depends on a subset of at most $k$ variables. We make two main contributions: - W…

Learning Theory

Lower Bounds for Greedy Teaching Set Constructions

2025-05-06 · Spencer Compton, Chirag Pabbaraju, Nikita Zhivotovskiy

A fundamental open problem in learning theory is to characterize the best-case teaching dimension $\operatorname{TS}_{\min}$ of a concept class $\mathcal{C}$ with finite VC dimension $d$. Resolving this problem will, in …

Learning Theory

Towards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework

2025-04-30 · Ankit Amrutkar, Björn Kampa, Volkmar Schulz, Johannes Stegmaier 외

Computer-generated holography (CGH) enables applications in holographic augmented reality (AR), 3D displays, systems neuroscience, and optical trapping. The fundamental challenge in CGH is solving the inverse problem of …

BenchmarkingLearning TheoryModel SelectionRetrieval+1

Data Selection for ERMs

2025-04-20 · Steve Hanneke, Shay Moran, Alexander Shlimovich, Amir Yehudayoff

Learning theory has traditionally followed a model-centric approach, focusing on designing optimal algorithms for a fixed natural learning task (e.g., linear classification or regression). In this paper, we adopt a compl…

Binary ClassificationLearning Theoryregression
1–20 / 852 다음 →