{"total":60,"rows":[{"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":"2106.03795","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","created":"2021-06-07","cited_by_count":44,"area":null},{"id":"2102.05375","title":"Strength of Minibatch Noise in SGD","created":"2021-02-10","cited_by_count":39,"area":null},{"id":"2104.10719","title":"A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection","created":"2021-04-21","cited_by_count":31,"area":null},{"id":"2106.04881","title":"Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms","created":"2021-06-09","cited_by_count":23,"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":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"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":"2305.05611","title":"Metric Space Magnitude and Generalisation in Neural Networks","created":"2023-05-09","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":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2204.08624","title":"Topology and geometry of data manifold in deep learning","created":"2022-04-19","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":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2201.12332","title":"On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2209.08951","title":"Generalization Bounds for Stochastic Gradient Descent via Localized $\\varepsilon$-Covers","created":"2022-09-19","cited_by_count":11,"area":null},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11,"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":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2203.12330","title":"Predicting the generalization gap in neural networks using topological data analysis","created":"2022-03-23","cited_by_count":9,"area":null},{"id":"2205.11361","title":"Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent","created":"2022-05-23","cited_by_count":9,"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":"2404.17442","title":"Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets","created":"2024-04-26","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":"2105.14677","title":"Characterization of Generalizability of Spike Timing Dependent Plasticity trained Spiking Neural Networks","created":"2021-05-31","cited_by_count":8,"area":null},{"id":"2302.11618","title":"Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles","created":"2023-02-22","cited_by_count":8,"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":"2205.06689","title":"Heavy-Tail Phenomenon in Decentralized SGD","created":"2022-05-13","cited_by_count":6,"area":null},{"id":"2205.13799","title":"Generalization Bounds for Gradient Methods via Discrete and Continuous Prior","created":"2022-05-27","cited_by_count":5,"area":null},{"id":"2306.03406","title":"Deep neural networks architectures from the perspective of manifold learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2406.02234","title":"On the Limitations of Fractal Dimension as a Measure of Generalization","created":"2024-06-04","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":"2312.00427","title":"From Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGD","created":"2023-12-01","cited_by_count":4,"area":null},{"id":"2402.01382","title":"Emergence of heavy tails in homogenized stochastic gradient descent","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2406.04047","title":"Slicing Mutual Information Generalization Bounds for Neural Networks","created":"2024-06-06","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":"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":"2503.22478","title":"Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2504.02873","title":"Short-PHD: Detecting Short LLM-generated Text with Topological Data Analysis After Off-topic Content Insertion","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2604.19740","title":"Generalization at the Edge of Stability","created":"2026-04-21","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":"2606.03338","title":"IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2303.17109","title":"Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models","created":"2023-03-30","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":"2507.06775","title":"Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2206.04359","title":"Learning Non-Vacuous Generalization Bounds from Optimization","created":"2022-06-09","cited_by_count":0,"area":null},{"id":"2402.12828","title":"Tracking the Median of Gradients with a Stochastic Proximal Point Method","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2507.02103","title":"What Neuroscience Can Teach AI About Learning in Continuously Changing Environments","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.12834","title":"Optimal Condition for Initialization Variance in Deep Neural Networks: An SGD Dynamics Perspective","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2605.13913","title":"A Survey on Data-Dependent Worst-Case Generalization Bounds","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.00293","title":"Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.08308","title":"Fourier fractal dimension to predict the generalization of deep neural networks","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.03377","title":"Spectral Signatures of Large Language Models","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2609.12994","title":"Dimension-Corrected Hitting Times for Heavy-Tailed Spectral Emergence in Neural Optimizer Dynamics","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}