{"total":142,"rows":[{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"area":null},{"id":"2103.13883","title":"Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning","created":"2021-03-25","cited_by_count":42,"area":"offlinerl"},{"id":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42,"area":null},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40,"area":null},{"id":"2107.13171","title":"Learning with Multiclass AUC: Theory and Algorithms","created":"2021-07-28","cited_by_count":35,"area":null},{"id":"2307.14619","title":"Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior","created":"2023-07-27","cited_by_count":33,"area":null},{"id":"2411.02544","title":"Pretrained transformer efficiently learns low-dimensional target functions in-context","created":"2024-11-04","cited_by_count":31,"area":null},{"id":"2203.02496","title":"Learning from Label Proportions by Learning with Label Noise","created":"2022-03-04","cited_by_count":30,"area":null},{"id":"2108.08887","title":"Risk Bounds and Calibration for a Smart Predict-then-Optimize Method","created":"2021-08-19","cited_by_count":29,"area":null},{"id":"2302.02334","title":"Revisiting Discriminative vs. Generative Classifiers: Theory and Implications","created":"2023-02-05","cited_by_count":29,"area":null},{"id":"2110.12351","title":"Integrated Conditional Estimation-Optimization","created":"2021-10-24","cited_by_count":25,"area":null},{"id":"2302.12383","title":"Generalization Analysis for Contrastive Representation Learning","created":"2023-02-24","cited_by_count":25,"area":null},{"id":"2112.01387","title":"Generalizing Off-Policy Learning under Sample Selection Bias","created":"2021-12-02","cited_by_count":16,"area":null},{"id":"2209.05150","title":"Bounding the Rademacher Complexity of Fourier neural operators","created":"2022-09-12","cited_by_count":16,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2402.03256","title":"Decision-Focused Learning with Directional Gradients","created":"2024-02-05","cited_by_count":16,"area":null},{"id":"2203.14493","title":"ARCS: Accurate Rotation and Correspondence Search","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2310.13220","title":"Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens","created":"2023-10-20","cited_by_count":15,"area":null},{"id":"2405.09782","title":"Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection","created":"2024-05-16","cited_by_count":14,"area":null},{"id":"2207.12877","title":"Representing Random Utility Choice Models with Neural Networks","created":"2022-07-26","cited_by_count":13,"area":null},{"id":"2403.14917","title":"Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective","created":"2024-03-22","cited_by_count":13,"area":null},{"id":"2102.00678","title":"Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification","created":"2021-02-01","cited_by_count":12,"area":null},{"id":"2306.03288","title":"Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization","created":"2023-06-05","cited_by_count":12,"area":null},{"id":"2402.08082","title":"Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian probability distributions","created":"2024-02-12","cited_by_count":12,"area":"diffusion"},{"id":"2410.11275","title":"Shallow diffusion networks provably learn hidden low-dimensional structure","created":"2024-10-15","cited_by_count":12,"area":"diffusion"},{"id":"2112.04364","title":"Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks","created":"2021-12-08","cited_by_count":11,"area":null},{"id":"2305.09557","title":"Learning from Aggregated Data: Curated Bags versus Random Bags","created":"2023-05-16","cited_by_count":11,"area":null},{"id":"2309.02028","title":"Non-Parametric Representation Learning with Kernels","created":"2023-09-05","cited_by_count":11,"area":null},{"id":"2311.04550","title":"Regression with Cost-based Rejection","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2512.23017","title":"Merge before Forget: A Single LoRA Continual Learning via Continual Merging","created":"2025-12-28","cited_by_count":11,"area":null},{"id":"2309.08044","title":"How many Neurons do we need? A refined Analysis for Shallow Networks trained with Gradient Descent","created":"2023-09-14","cited_by_count":10,"area":null},{"id":"2310.01225","title":"A path-norm toolkit for modern networks: consequences, promises and challenges","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2503.00626","title":"Dissecting the Impact of Model Misspecification in Data-driven Optimization","created":"2025-03-01","cited_by_count":10,"area":null},{"id":"2105.05026","title":"Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization","created":"2021-05-10","cited_by_count":9,"area":null},{"id":"2202.08070","title":"On Measuring Excess Capacity in Neural Networks","created":"2022-02-16","cited_by_count":9,"area":null},{"id":"2210.02871","title":"Self-Distillation for Further Pre-training of Transformers","created":"2022-09-30","cited_by_count":9,"area":"distill"},{"id":"2512.23947","title":"Improved Balanced Classification with Theoretically Grounded Loss Functions","created":"2025-12-30","cited_by_count":9,"area":null},{"id":"2106.03589","title":"Nonparametric adaptive control and prediction: theory and randomized algorithms","created":"2021-06-07","cited_by_count":8,"area":null},{"id":"2112.12303","title":"Learning with Proper Partial Labels","created":"2021-12-23","cited_by_count":8,"area":null},{"id":"2206.01399","title":"Generalization for multiclass classification with overparameterized linear models","created":"2022-06-03","cited_by_count":8,"area":null},{"id":"2302.12712","title":"Amortised Invariance Learning for Contrastive Self-Supervision","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2403.06871","title":"On the Generalization Ability of Unsupervised Pretraining","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2101.05514","title":"Entangled Kernels -- Beyond Separability","created":"2021-01-14","cited_by_count":7,"area":null},{"id":"2210.11855","title":"Learning in RKHM: a $C^*$-Algebraic Twist for Kernel Machines","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2305.13588","title":"Deep Learning with Kernels through RKHM and the Perron-Frobenius Operator","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2307.11030","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","created":"2023-07-20","cited_by_count":7,"area":"distill"},{"id":"2310.15330","title":"Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2505.16341","title":"A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"area":"deeprl"},{"id":"2101.11525","title":"Calibrating and Improving Graph Contrastive Learning","created":"2021-01-27","cited_by_count":6,"area":null},{"id":"2207.01555","title":"Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2305.11165","title":"The noise level in linear regression with dependent data","created":"2023-05-18","cited_by_count":6,"area":null},{"id":"2305.15901","title":"Consistent Optimal Transport with Empirical Conditional Measures","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2405.20447","title":"Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2406.05090","title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2104.14173","title":"Fine-grained Generalization Analysis of Vector-valued Learning","created":"2021-04-29","cited_by_count":5,"area":null},{"id":"2206.03827","title":"Fast Kernel Methods for Generic Lipschitz Losses via $p$-Sparsified Sketches","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2106.00115","title":"Fine-grained Generalization Analysis of Structured Output Prediction","created":"2021-05-31","cited_by_count":4,"area":null},{"id":"2106.05397","title":"From inexact optimization to learning via gradient concentration","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2205.07050","title":"DECONET: an Unfolding Network for Analysis-based Compressed Sensing with Generalization Error Bounds","created":"2022-05-14","cited_by_count":4,"area":null},{"id":"2209.03447","title":"Blessing of Class Diversity in Pre-training","created":"2022-09-07","cited_by_count":4,"area":null},{"id":"2305.16475","title":"Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2405.10302","title":"Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift","created":"2024-05-16","cited_by_count":4,"area":null},{"id":"2405.16639","title":"A direct proof of a unified law of robustness for Bregman divergence losses","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2410.07427","title":"A Generalization Bound for a Family of Implicit Networks","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2411.13733","title":"On Generalization Bounds for Neural Networks with Low Rank Layers","created":"2024-11-20","cited_by_count":4,"area":null},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2602.17554","title":"A Theoretical Framework for Modular Learning of Robust Generative Models","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2106.08864","title":"Multi-Class Classification from Single-Class Data with Confidences","created":"2021-06-16","cited_by_count":3,"area":null},{"id":"2205.10055","title":"A Case of Exponential Convergence Rates for SVM","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2205.13255","title":"Active Labeling: Streaming Stochastic Gradients","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2208.01148","title":"Boosted Off-Policy Learning","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2211.04226","title":"Gradient-enhanced deep neural network approximations","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2308.05617","title":"A Neural Network Based Choice Model for Assortment Optimization","created":"2023-08-10","cited_by_count":3,"area":null},{"id":"2508.09427","title":"Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2203.12836","title":"Learning from Label Proportions with Instance-wise Consistency","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2303.05582","title":"Generalization analysis of an unfolding network for analysis-based Compressed Sensing","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2306.06894","title":"A Generalized Unbiased Risk Estimator for Learning with Augmented Classes","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2405.20278","title":"Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2410.09156","title":"On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2502.01310","title":"A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2505.22359","title":"Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2604.27723","title":"Optimized Deferral for Imbalanced Settings","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2106.10535","title":"Learning and Generalization in Overparameterized Normalizing Flows","created":"2021-06-19","cited_by_count":1,"area":null},{"id":"2203.13446","title":"Randomized Policy Optimization for Optimal Stopping","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2212.01689","title":"Learning-Assisted Algorithm Unrolling for Online Optimization with Budget Constraints","created":"2022-12-03","cited_by_count":1,"area":null},{"id":"2304.14474","title":"A Chain Rule for the Expected Suprema of Bernoulli Processes","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2308.07047","title":"No Regularization is Needed: An Efficient and Effective Model for Incomplete Label Distribution Learning","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2311.01589","title":"A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning","created":"2023-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2402.13106","title":"On Generalization Bounds for Deep Compound Gaussian Neural Networks","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2408.08533","title":"Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2410.22574","title":"Inference in Partially Linear Models under Dependent Data with Deep Neural Networks","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2412.12449","title":"Adversarially robust generalization theory via Jacobian regularization for deep neural networks","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2501.18864","title":"Flatness Guided Test-Time Adaptation for Vision-Language Models","created":"2025-01-31","cited_by_count":1,"area":"mllm"},{"id":"2507.08518","title":"Data Depth as a Risk","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2509.23474","title":"Statistical Learning Guarantees for Group-Invariant Barron Functions","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.03993","title":"Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2510.25458","title":"Scalable Utility-Aware Multiclass Calibration","created":"2025-10-29","cited_by_count":1,"area":null}],"next_cursor":"100"}