{"total":397,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2010.11895","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?","created":"2020-10-22","cited_by_count":136,"area":"offlinerl"},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135,"area":"alignment"},{"id":"2202.02794","title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","created":"2022-02-06","cited_by_count":133,"area":null},{"id":"2402.01868","title":"Challenges in Training PINNs: A Loss Landscape Perspective","created":"2024-02-02","cited_by_count":113,"area":null},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"area":null},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86,"area":null},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2106.15535","title":"Subgroup Generalization and Fairness of Graph Neural Networks","created":"2021-06-29","cited_by_count":69,"area":null},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58,"area":null},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46,"area":null},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45,"area":null},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44,"area":null},{"id":"2306.01323","title":"Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?","created":"2023-06-02","cited_by_count":41,"area":null},{"id":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40,"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":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2202.08545","title":"Information Theory with Kernel Methods","created":"2022-02-17","cited_by_count":37,"area":null},{"id":"2408.12186","title":"Transformers are Minimax Optimal Nonparametric In-Context Learners","created":"2024-08-22","cited_by_count":37,"area":null},{"id":"2407.12332","title":"Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34,"area":null},{"id":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33,"area":null},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33,"area":null},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2207.06503","title":"Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations","created":"2022-07-13","cited_by_count":32,"area":null},{"id":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30,"area":null},{"id":"2106.03212","title":"Towards an Understanding of Benign Overfitting in Neural Networks","created":"2021-06-06","cited_by_count":30,"area":null},{"id":"2110.03874","title":"Uncertainty quantification in the Bradley-Terry-Luce model","created":"2021-10-08","cited_by_count":29,"area":null},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28,"area":null},{"id":"2103.11003","title":"Differentially private inference via noisy optimization","created":"2021-03-19","cited_by_count":27,"area":null},{"id":"2112.03865","title":"Universalizing Weak Supervision","created":"2021-12-07","cited_by_count":27,"area":null},{"id":"2205.06308","title":"An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings","created":"2022-05-12","cited_by_count":27,"area":null},{"id":"2312.15995","title":"Generalization in Kernel Regression Under Realistic Assumptions","created":"2023-12-26","cited_by_count":27,"area":null},{"id":"2102.00479","title":"Fast Rates for the Regret of Offline Reinforcement Learning","created":"2021-01-31","cited_by_count":26,"area":"offlinerl"},{"id":"2102.05320","title":"An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians","created":"2021-02-10","cited_by_count":25,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2405.20272","title":"Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable","created":"2024-05-30","cited_by_count":25,"area":"safety"},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2107.07480","title":"Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update","created":"2021-07-15","cited_by_count":23,"area":null},{"id":"2410.01917","title":"Provably Accurate Shapley Value Estimation via Leverage Score Sampling","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","cited_by_count":22,"area":null},{"id":"2102.01229","title":"Doubly robust Thompson sampling for linear payoffs","created":"2021-02-01","cited_by_count":21,"area":null},{"id":"2102.03646","title":"Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates","created":"2021-02-06","cited_by_count":21,"area":null},{"id":"2105.15081","title":"Optimal Spectral Recovery of a Planted Vector in a Subspace","created":"2021-05-31","cited_by_count":21,"area":null},{"id":"2303.07152","title":"Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning","created":"2023-03-13","cited_by_count":21,"area":null},{"id":"2311.15722","title":"GLIME: General, Stable and Local LIME Explanation","created":"2023-11-27","cited_by_count":21,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2110.00151","title":"Lagrangian Inference for Ranking Problems","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2405.16644","title":"Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2109.11502","title":"Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programming","created":"2021-09-23","cited_by_count":17,"area":null},{"id":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2101.08421","title":"Optimal Full Ranking from Pairwise Comparisons","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2106.06251","title":"On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting","created":"2021-06-11","cited_by_count":16,"area":"distill"},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16,"area":"offlinerl"},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2212.09961","title":"Uncertainty Quantification of MLE for Entity Ranking with Covariates","created":"2022-12-20","cited_by_count":16,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","cited_by_count":15,"area":null},{"id":"2302.02552","title":"Adapting to Continuous Covariate Shift via Online Density Ratio Estimation","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2111.05198","title":"Harmless interpolation in regression and classification with structured features","created":"2021-11-09","cited_by_count":14,"area":null},{"id":"2209.13435","title":"Scaling Laws For Deep Learning Based Image Reconstruction","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2111.07430","title":"Safe Online Convex Optimization with Unknown Linear Safety Constraints","created":"2021-11-14","cited_by_count":13,"area":null},{"id":"2202.13157","title":"High Dimensional Statistical Estimation under Uniformly Dithered One-bit Quantization","created":"2022-02-26","cited_by_count":13,"area":null},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2206.07553","title":"On the fast convergence of minibatch heavy ball momentum","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2105.10475","title":"Generalization Error Bound for Hyperbolic Ordinal Embedding","created":"2021-05-21","cited_by_count":12,"area":null},{"id":"2302.09699","title":"Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks","created":"2023-02-20","cited_by_count":12,"area":null},{"id":"2302.11962","title":"Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods","created":"2023-02-23","cited_by_count":12,"area":null},{"id":"2302.14753","title":"Learning Hidden Markov Models Using Conditional Samples","created":"2023-02-28","cited_by_count":12,"area":null},{"id":"2310.19733","title":"Differentially Private Reward Estimation with Preference Feedback","created":"2023-10-30","cited_by_count":12,"area":"alignment"},{"id":"2504.09708","title":"Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization","created":"2025-04-13","cited_by_count":12,"area":null},{"id":"2112.14233","title":"Multitask Learning and Bandits via Robust Statistics","created":"2021-12-28","cited_by_count":11,"area":null},{"id":"2306.00127","title":"Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2309.11617","title":"Statistical Complexity of Quantum Learning","created":"2023-09-20","cited_by_count":11,"area":null},{"id":"2401.01599","title":"Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay","created":"2024-01-03","cited_by_count":11,"area":null},{"id":"2402.03625","title":"Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2405.09312","title":"Agnostic Active Learning of Single Index Models with Linear Sample Complexity","created":"2024-05-15","cited_by_count":11,"area":null},{"id":"2405.13453","title":"A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2406.11151","title":"Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2102.06697","title":"Matching Point Sets with Quantum Circuit Learning","created":"2021-02-12","cited_by_count":10,"area":null},{"id":"2103.04031","title":"Accumulation of Sub-Sampling Matrices with Applications to Statistical Computation","created":"2021-03-06","cited_by_count":10,"area":null},{"id":"2107.09802","title":"Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates","created":"2021-07-20","cited_by_count":10,"area":null},{"id":"2111.07126","title":"On the Statistical Benefits of Curriculum Learning","created":"2021-11-13","cited_by_count":10,"area":null},{"id":"2208.12042","title":"Efficient Truncated Linear Regression with Unknown Noise Variance","created":"2022-08-25","cited_by_count":10,"area":null},{"id":"2310.06793","title":"Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning","created":"2023-10-10","cited_by_count":10,"area":null},{"id":"2403.00666","title":"Sharp bounds for max-sliced Wasserstein distances","created":"2024-03-01","cited_by_count":10,"area":null},{"id":"2502.00620","title":"Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions","created":"2025-02-02","cited_by_count":10,"area":null},{"id":"2502.06719","title":"Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2111.12823","title":"Fairness for AUC via Feature Augmentation","created":"2021-11-24","cited_by_count":9,"area":null},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2212.14562","title":"Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2411.05234","title":"Performative Reinforcement Learning with Linear Markov Decision Process","created":"2024-11-07","cited_by_count":9,"area":"deeprl"},{"id":"2501.19183","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2102.02450","title":"Sharper Sub-Weibull Concentrations","created":"2021-02-04","cited_by_count":8,"area":null},{"id":"2106.11068","title":"Affine-Invariant Integrated Rank-Weighted Depth: Definition, Properties and Finite Sample Analysis","created":"2021-06-21","cited_by_count":8,"area":null}],"next_cursor":"100"}