Papers Learning Theory
“Learning Theory” 태그가 달린 논문 852편 · 필터 해제
On the Hardness of Bandit Learning
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 TheoryFinding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach
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+3The Universality Lens: Why Even Highly Over-Parametrized Models Learn Well
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 TheoryLearning Theory of Decentralized Robust Kernel-Based Learning Algorithm
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 TheoryWhat Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness
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 TheoryA Machine Learning Theory Perspective on Strategic Litigation
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 TheoryVariational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
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 InferenceLearning DNF through Generalized Fourier Representations
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 TheoryDistribution free M-estimation
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 OptimizationAttribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate
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 learningA Semantic Change Detection Network Based on Boundary Detection and Task Interaction for High-Resolution Remote Sensing Images
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+1Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
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 LearningData-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review
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 GenerationAn Asymptotic Equation Linking WAIC and WBIC in Singular Models
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 SelectionInformation Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
[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 TheoryLearning Guarantee of Reward Modeling Using Deep Neural Networks
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 TheoryNew Statistical and Computational Results for Learning Junta Distributions
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 TheoryLower Bounds for Greedy Teaching Set Constructions
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 TheoryTowards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework
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+1Data Selection for ERMs
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