{"list":"other","total":56,"rows":[{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239},{"id":"1901.06053","title":"A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks","created":"2019-01-18","cited_by_count":214},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"1906.02506","title":"Practical Deep Learning with Bayesian Principles","created":"2019-06-06","cited_by_count":158},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"1806.04854","title":"Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam","created":"2018-06-13","cited_by_count":131},{"id":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"2006.04740","title":"The Heavy-Tail Phenomenon in SGD","created":"2020-06-08","cited_by_count":124},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86},{"id":"2006.15081","title":"On the Generalization Benefit of Noise in Stochastic Gradient Descent","created":"2020-06-26","cited_by_count":82},{"id":"1802.07044","title":"The Description Length of Deep Learning Models","created":"2018-02-20","cited_by_count":72},{"id":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65},{"id":"2207.02628","title":"The alignment property of SGD noise and how it helps select flat minima: A stability analysis","created":"2022-07-06","cited_by_count":64},{"id":"2410.24206","title":"Understanding Optimization in Deep Learning with Central Flows","created":"2024-10-31","cited_by_count":64},{"id":"2210.03294","title":"Understanding Edge-of-Stability Training Dynamics with a Minimalist Example","created":"2022-10-07","cited_by_count":56},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53},{"id":"2212.07469","title":"Learning threshold neurons via the \"edge of stability\"","created":"2022-12-14","cited_by_count":51},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50},{"id":"1906.09069","title":"First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise","created":"2019-06-21","cited_by_count":44},{"id":"2202.02831","title":"Anticorrelated Noise Injection for Improved Generalization","created":"2022-02-06","cited_by_count":42},{"id":"2305.11788","title":"Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability","created":"2023-05-19","cited_by_count":42},{"id":"2210.04860","title":"Second-order regression models exhibit progressive sharpening to the edge of stability","created":"2022-10-10","cited_by_count":40},{"id":"2206.04172","title":"Beyond the Edge of Stability via Two-step Gradient Updates","created":"2022-06-08","cited_by_count":38},{"id":"2302.08982","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability","created":"2023-02-17","cited_by_count":36},{"id":"2002.10060","title":"Handling the Positive-Definite Constraint in the Bayesian Learning Rule","created":"2020-02-24","cited_by_count":31},{"id":"2412.20553","title":"Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD","created":"2024-12-29","cited_by_count":30},{"id":"2206.04613","title":"Explicit Regularization in Overparametrized Models via Noise Injection","created":"2022-06-09","cited_by_count":26},{"id":"2310.17087","title":"Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult","created":"2023-10-26","cited_by_count":25},{"id":"2302.08692","title":"SAM operates far from home: eigenvalue regularization as a dynamical phenomenon","created":"2023-02-17","cited_by_count":24},{"id":"1910.09626","title":"Non-Gaussianity of Stochastic Gradient Noise","created":"2019-10-21","cited_by_count":22},{"id":"2311.02076","title":"Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos","created":"2023-11-03","cited_by_count":22},{"id":"2305.13064","title":"Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond","created":"2023-05-22","cited_by_count":21},{"id":"2409.14396","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","created":"2024-09-22","cited_by_count":20},{"id":"1910.00195","title":"How noise affects the Hessian spectrum in overparameterized neural networks","created":"2019-10-01","cited_by_count":17},{"id":"2205.11787","title":"Quadratic models for understanding catapult dynamics of neural networks","created":"2022-05-24","cited_by_count":17},{"id":"2309.12488","title":"Sharpness-Aware Minimization and the Edge of Stability","created":"2023-09-21","cited_by_count":17},{"id":"2310.01687","title":"From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression","created":"2023-10-02","cited_by_count":17},{"id":"2102.04297","title":"Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise","created":"2021-02-08","cited_by_count":14},{"id":"2306.08553","title":"Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach","created":"2023-06-14","cited_by_count":14},{"id":"1709.01434","title":"A Generic Approach for Escaping Saddle points","created":"2017-09-05","cited_by_count":13},{"id":"2306.07850","title":"Exact Mean Square Linear Stability Analysis for SGD","created":"2023-06-13","cited_by_count":11},{"id":"2211.12624","title":"Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization","created":"2022-11-22","cited_by_count":6},{"id":"2305.19243","title":"Improving Generalization of Complex Models under Unbounded Loss Using PAC-Bayes Bounds","created":"2023-05-30","cited_by_count":6},{"id":"2411.04421","title":"Variational Low-Rank Adaptation Using IVON","created":"2024-11-07","cited_by_count":5},{"id":"2311.15051","title":"Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults","created":"2023-11-25","cited_by_count":3}],"next_cursor":null}