{"total":43,"rows":[{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70,"area":null},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27,"area":null},{"id":"2203.02474","title":"Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms","created":"2022-03-04","cited_by_count":22,"area":null},{"id":"2301.11885","title":"Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions","created":"2023-01-27","cited_by_count":15,"area":null},{"id":"2302.02766","title":"Generalization Bounds with Data-dependent Fractal Dimensions","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2305.18383","title":"A Three-regime Model of Network Pruning","created":"2023-05-28","cited_by_count":15,"area":null},{"id":"2206.02604","title":"Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning","created":"2022-06-06","cited_by_count":14,"area":null},{"id":"2205.08187","title":"Deep neural networks with dependent weights: Gaussian Process mixture limit, heavy tails, sparsity and compressibility","created":"2022-05-17","cited_by_count":13,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2206.01274","title":"Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares","created":"2022-06-02","cited_by_count":12,"area":null},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2303.05369","title":"Data-dependent Generalization Bounds via Variable-Size Compressibility","created":"2023-03-09","cited_by_count":9,"area":null},{"id":"2406.04657","title":"From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks","created":"2024-06-07","cited_by_count":9,"area":null},{"id":"2304.02911","title":"Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2410.15637","title":"Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2205.06689","title":"Heavy-Tail Phenomenon in Decentralized SGD","created":"2022-05-13","cited_by_count":6,"area":null},{"id":"2306.08125","title":"Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2405.17529","title":"Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2307.02501","title":"Generalization Guarantees via Algorithm-dependent Rademacher Complexity","created":"2023-07-04","cited_by_count":4,"area":null},{"id":"2310.18455","title":"Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent","created":"2023-10-27","cited_by_count":3,"area":null},{"id":"2403.02051","title":"Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2507.09093","title":"Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization","created":"2025-07-12","cited_by_count":3,"area":null},{"id":"2510.19389","title":"ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2302.05516","title":"Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2402.05101","title":"Tighter Generalisation Bounds via Interpolation","created":"2024-02-07","cited_by_count":2,"area":null},{"id":"2502.15540","title":"Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2507.17725","title":"On the Interaction of Compressibility and Adversarial Robustness","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2507.17748","title":"Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2511.04456","title":"Federated Stochastic Minimax Optimization under Heavy-Tailed Noises","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2605.26000","title":"Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2309.13575","title":"Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantization","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2410.13954","title":"Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2504.18455","title":"Multiview Representation Learning via Distributed Joint Latent Space Structuring","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2202.09276","title":"Geometric Regularization from Overparameterization","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2509.00046","title":"Exploring and Reshaping the Weight Distribution in LLM","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2511.15634","title":"R\\'enyi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincar\\'e Inequalities","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2605.07634","title":"Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2609.34731","title":"Information-Theoretic Analysis of Next-Token Prediction under Markovian Data","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}