{"total":15,"rows":[{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2206.00164","title":"A Theoretical Framework for Inference Learning","created":"2022-06-01","cited_by_count":17,"area":null},{"id":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2206.09379","title":"0/1 Deep Neural Networks via Block Coordinate Descent","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2406.17296","title":"BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2101.03419","title":"Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods","created":"2021-01-09","cited_by_count":5,"area":null},{"id":"2205.05428","title":"An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity","created":"2022-05-11","cited_by_count":5,"area":null},{"id":"2208.14318","title":"Convergence Rates of Training Deep Neural Networks via Alternating Minimization Methods","created":"2022-08-30","cited_by_count":4,"area":null},{"id":"2112.09341","title":"Personalized On-Device E-health Analytics with Decentralized Block Coordinate Descent","created":"2021-12-17","cited_by_count":2,"area":null},{"id":"2303.06815","title":"On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2412.09556","title":"Enhancing Convergence of Decentralized Gradient Tracking under the KL Property","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2503.08489","title":"A Triple-Inertial Accelerated Alternating Optimization Method for Deep Learning Training","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2101.06940","title":"Learning DNN networks using un-rectifying ReLU with compressed sensing application","created":"2021-01-18","cited_by_count":0,"area":null},{"id":"2506.12037","title":"Exploiting Block Coordinate Descent for Cost-Effective LLM Model Training","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2510.22667","title":"Block Coordinate Descent for Neural Networks Provably Finds Global Minima","created":"2025-10-26","cited_by_count":0,"area":null}],"next_cursor":null}