{"total":37,"rows":[{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2109.02355","title":"A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning","created":"2021-09-06","cited_by_count":57,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2206.08684","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26,"area":null},{"id":"2302.06210","title":"Precise Asymptotic Analysis of Deep Random Feature Models","created":"2023-02-13","cited_by_count":22,"area":null},{"id":"2201.06142","title":"Towards Sample-efficient Overparameterized Meta-learning","created":"2022-01-16","cited_by_count":21,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2104.14132","title":"Generalization Guarantees for Neural Architecture Search with Train-Validation Split","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2301.07605","title":"Strong inductive biases provably prevent harmless interpolation","created":"2023-01-18","cited_by_count":10,"area":null},{"id":"2502.01347","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2510.08123","title":"High-dimensional Analysis of Synthetic Data Selection","created":"2025-10-09","cited_by_count":7,"area":null},{"id":"2303.01213","title":"DSD$^2$: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?","created":"2023-03-02","cited_by_count":6,"area":null},{"id":"2310.13572","title":"Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space","created":"2023-10-20","cited_by_count":6,"area":null},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2205.05662","title":"Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2204.02678","title":"Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2311.05061","title":"Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2502.01330","title":"Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2302.13259","title":"Can we avoid Double Descent in Deep Neural Networks?","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2406.02769","title":"Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2208.12926","title":"Overparameterization from Computational Constraints","created":"2022-08-27","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2506.17187","title":"Optimal Implicit Bias in Linear Regression","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2510.12249","title":"Optimal Regularization for Performative Learning","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2308.16596","title":"The Quest of Finding the Antidote to Sparse Double Descent","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2312.03951","title":"Understanding the Role of Optimization in Double Descent","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2405.07679","title":"Class-wise Activation Unravelling the Engima of Deep Double Descent","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2405.20194","title":"Occam Gradient Descent","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2411.15795","title":"Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2507.09940","title":"Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2510.16250","title":"One-Bit Quantization for Random Features Models","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2607.16027","title":"Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints","created":"2026-07-17","cited_by_count":0,"area":null}],"next_cursor":null}