{"total":58,"rows":[{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161,"area":null},{"id":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2305.10633","title":"Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models","created":"2023-05-18","cited_by_count":61,"area":null},{"id":"2102.04401","title":"The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals","created":"2021-02-08","cited_by_count":52,"area":null},{"id":"2402.03220","title":"The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents","created":"2024-02-05","cited_by_count":52,"area":null},{"id":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"area":null},{"id":"2202.05258","title":"Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2112.03898","title":"Lattice-Based Methods Surpass Sum-of-Squares in Clustering","created":"2021-12-07","cited_by_count":25,"area":null},{"id":"2101.08303","title":"From Local Pseudorandom Generators to Hardness of Learning","created":"2021-01-20","cited_by_count":24,"area":null},{"id":"2108.09805","title":"Efficient Algorithms for Learning from Coarse Labels","created":"2021-08-22","cited_by_count":21,"area":null},{"id":"2106.10744","title":"On the Cryptographic Hardness of Learning Single Periodic Neurons","created":"2021-06-20","cited_by_count":20,"area":null},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2102.00434","title":"The Connection Between Approximation, Depth Separation and Learnability in Neural Networks","created":"2021-01-31","cited_by_count":19,"area":null},{"id":"2405.15480","title":"Fundamental computational limits of weak learnability in high-dimensional multi-index models","created":"2024-05-24","cited_by_count":19,"area":null},{"id":"2406.01461","title":"Hardness of Learning Neural Networks under the Manifold Hypothesis","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2101.01152","title":"Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise","created":"2021-01-04","cited_by_count":17,"area":null},{"id":"2307.15804","title":"On Single Index Models beyond Gaussian Data","created":"2023-07-28","cited_by_count":17,"area":null},{"id":"2107.10209","title":"Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations","created":"2021-07-21","cited_by_count":15,"area":null},{"id":"2304.10524","title":"Learning Narrow One-Hidden-Layer ReLU Networks","created":"2023-04-20","cited_by_count":14,"area":null},{"id":"2401.01869","title":"On the hardness of learning under symmetries","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2403.04744","title":"SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions","created":"2024-03-07","cited_by_count":13,"area":null},{"id":"2210.04389","title":"DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2302.07426","title":"Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy","created":"2023-02-15","cited_by_count":10,"area":null},{"id":"2205.16003","title":"Learning (Very) Simple Generative Models Is Hard","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2411.07536","title":"Model Stealing for Any Low-Rank Language Model","created":"2024-11-12","cited_by_count":9,"area":null},{"id":"2102.05174","title":"On the Hardness of PAC-learning Stabilizer States with Noise","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2502.06443","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2307.12496","title":"A faster and simpler algorithm for learning shallow networks","created":"2023-07-24","cited_by_count":7,"area":null},{"id":"2111.04727","title":"Efficiently Learning Any One Hidden Layer ReLU Network From Queries","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2305.16892","title":"Feature Adaptation for Sparse Linear Regression","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2404.03774","title":"Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning","created":"2024-04-04","cited_by_count":6,"area":"deeprl"},{"id":"2410.21426","title":"Sum-of-squares lower bounds for Non-Gaussian Component Analysis","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2411.15669","title":"Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2205.13531","title":"Learning ReLU networks to high uniform accuracy is intractable","created":"2022-05-26","cited_by_count":5,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2411.14349","title":"Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2411.15385","title":"Gradient dynamics for low-rank fine-tuning beyond kernels","created":"2024-11-23","cited_by_count":5,"area":null},{"id":"2307.12840","title":"Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials","created":"2023-07-24","cited_by_count":4,"area":null},{"id":"2406.01766","title":"How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2502.16021","title":"Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2510.04115","title":"On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach","created":"2025-10-05","cited_by_count":4,"area":null},{"id":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2404.03272","title":"Cryptographic Hardness of Score Estimation","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2503.20879","title":"Quantum advantage for learning shallow neural networks with natural data distributions","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2605.22010","title":"Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2203.02824","title":"Distributional Hardness Against Preconditioned Lasso via Erasure-Robust Designs","created":"2022-03-05","cited_by_count":2,"area":null},{"id":"2209.08627","title":"Is Stochastic Gradient Descent Near Optimal?","created":"2022-09-18","cited_by_count":2,"area":null},{"id":"2305.16508","title":"Most Neural Networks Are Almost Learnable","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2511.11498","title":"Learning and Testing Convex Functions","created":"2025-11-14","cited_by_count":2,"area":null},{"id":"2603.17896","title":"A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2105.03594","title":"Learning stochastic decision trees","created":"2021-05-08","cited_by_count":1,"area":null},{"id":"2410.03477","title":"On the Hardness of Learning One Hidden Layer Neural Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2512.15987","title":"Provably Extracting the Features from a General Superposition","created":"2025-12-17","cited_by_count":1,"area":"mechinterp"},{"id":"2408.02045","title":"DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2609.13057","title":"Benign Loss Landscapes Can Coexist with Worst-Case Hardness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.02749","title":"Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}