{"total":29,"rows":[{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2102.04396","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","created":"2021-02-08","cited_by_count":35,"area":null},{"id":"2210.11662","title":"Local Bayesian optimization via maximizing probability of descent","created":"2022-10-21","cited_by_count":30,"area":null},{"id":"2306.12747","title":"Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2102.06604","title":"Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2111.07952","title":"Stochastic Gradient Line Bayesian Optimization for Efficient Noise-Robust Optimization of Parameterized Quantum Circuits","created":"2021-11-15","cited_by_count":7,"area":null},{"id":"2107.03331","title":"KOALA: A Kalman Optimization Algorithm with Loss Adaptivity","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2602.03232","title":"BayeSQP: Bayesian Optimization through Sequential Quadratic Programming","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2103.17132","title":"Empirically explaining SGD from a line search perspective","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2403.18506","title":"Faster Convergence for Transformer Fine-tuning with Line Search Methods","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2403.18519","title":"Improving Line Search Methods for Large Scale Neural Network Training","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2407.20650","title":"No learning rates needed: Introducing SALSA -- Stable Armijo Line Search Adaptation","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2508.09792","title":"Bayesian autoregression to optimize temporal Mat\\'ern kernel Gaussian process hyperparameters","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2102.10880","title":"A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2104.12949","title":"Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions","created":"2021-04-27","cited_by_count":0,"area":null},{"id":"2105.10915","title":"GOALS: Gradient-Only Approximations for Line Searches Towards Robust and Consistent Training of Deep Neural Networks","created":"2021-05-23","cited_by_count":0,"area":null},{"id":"2106.08767","title":"To Raise or Not To Raise: The Autonomous Learning Rate Question","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2106.13718","title":"Black Box Probabilistic Numerics","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2108.13880","title":"Using a one dimensional parabolic model of the full-batch loss to estimate learning rates during training","created":"2021-08-31","cited_by_count":0,"area":null},{"id":"2111.07058","title":"Bolstering Stochastic Gradient Descent with Model Building","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2305.13664","title":"Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2308.03102","title":"Learning-Rate-Free Learning: Dissecting D-Adaptation and Probabilistic Line Search","created":"2023-08-06","cited_by_count":0,"area":null},{"id":"2408.17145","title":"Painless Federated Learning: An Interplay of Line-Search and Extrapolation","created":"2024-08-30","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":"2505.00162","title":"Stochastic Subspace Descent Accelerated via Bi-fidelity Line Search","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2507.15485","title":"Information Preserving Line Search via Bayesian Optimization","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2609.33499","title":"The cost of useful natural gradient updates","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.02190","title":"Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}