{"total":43,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2108.06819","title":"EventHPE: Event-based 3D Human Pose and Shape Estimation","created":"2021-08-15","cited_by_count":42,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2103.03265","title":"Better SGD using Second-order Momentum","created":"2021-03-04","cited_by_count":15,"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":"2108.06834","title":"Human Pose and Shape Estimation from Single Polarization Images","created":"2021-08-15","cited_by_count":13,"area":null},{"id":"2604.05230","title":"Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2306.04985","title":"Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping","created":"2023-06-08","cited_by_count":10,"area":null},{"id":"2306.02527","title":"Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2211.08597","title":"SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates","created":"2022-11-16","cited_by_count":8,"area":null},{"id":"2402.11215","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","created":"2024-02-17","cited_by_count":8,"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":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2103.11154","title":"Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces","created":"2021-03-20","cited_by_count":5,"area":null},{"id":"2109.12213","title":"Adaptive Sampling Quasi-Newton Methods for Zeroth-Order Stochastic Optimization","created":"2021-09-24","cited_by_count":4,"area":null},{"id":"2308.04457","title":"A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2501.15941","title":"SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning","created":"2025-01-27","cited_by_count":4,"area":null},{"id":"2404.14758","title":"Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients","created":"2024-04-23","cited_by_count":3,"area":null},{"id":"2104.02865","title":"Quasi-Newton Quasi-Monte Carlo for variational Bayes","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2511.19716","title":"Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2602.03001","title":"Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2103.04392","title":"A Retrospective Approximation Approach for Smooth Stochastic Optimization","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2104.03804","title":"Exact Stochastic Second Order Deep Learning","created":"2021-04-08","cited_by_count":1,"area":null},{"id":"2111.14761","title":"Adaptive First- and Second-Order Algorithms for Large-Scale Machine Learning","created":"2021-11-29","cited_by_count":1,"area":null},{"id":"2205.09121","title":"On the efficiency of Stochastic Quasi-Newton Methods for Deep Learning","created":"2022-05-18","cited_by_count":1,"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":"2411.00112","title":"Derivative-Free Optimization via Finite Difference Approximation: An Experimental Study","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2205.08231","title":"Hyper-Learning for Gradient-Based Batch Size Adaptation","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2209.14975","title":"Causal Inference via Nonlinear Variable Decorrelation for Healthcare Applications","created":"2022-09-29","cited_by_count":0,"area":null},{"id":"2306.15444","title":"Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2310.12298","title":"Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2310.20574","title":"Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2410.11545","title":"A model learning framework for inferring the dynamics of transmission rate depending on exogenous variables for epidemic forecasts","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2502.20819","title":"Enhanced Derivative-Free Optimization Using Adaptive Correlation-Induced Finite Difference Estimators","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2508.16905","title":"Tri-Accel: Curvature-Aware Precision-Adaptive and Memory-Elastic Optimization for Efficient GPU Usage","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2605.16017","title":"Accelerated Gradient Descent for Faster Convergence with Minimal Overhead","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.02079","title":"FACT: A Simple and Efficient Framework for Active Finetuning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2609.13819","title":"Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics Simulators","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}