{"total":20,"rows":[{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78,"area":null},{"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":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2302.01228","title":"Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons","created":"2023-02-02","cited_by_count":14,"area":null},{"id":"2212.04129","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","created":"2022-12-08","cited_by_count":13,"area":null},{"id":"2208.08772","title":"Lifted Bregman Training of Neural Networks","created":"2022-08-18","cited_by_count":10,"area":null},{"id":"2307.16235","title":"Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey","created":"2023-07-30","cited_by_count":8,"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":"2105.07231","title":"Bilevel Programs Meet Deep Learning: A Unifying View on Inference Learning Methods","created":"2021-05-15","cited_by_count":5,"area":null},{"id":"2102.00267","title":"Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2201.00723","title":"A Mixed-Integer Programming Approach to Training Dense Neural Networks","created":"2022-01-03","cited_by_count":3,"area":null},{"id":"2410.12441","title":"A primal-dual algorithm for image reconstruction with input-convex neural network regularizers","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2105.00339","title":"Stochastic Block-ADMM for Training Deep Networks","created":"2021-05-01","cited_by_count":2,"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":"2402.08573","title":"Two Tales of Single-Phase Contrastive Hebbian Learning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2605.31022","title":"Augmented Lagrangian Predictive Coding","created":"2026-05-29","cited_by_count":1,"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},{"id":"2609.35174","title":"ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16429","title":"Taming Nonconvexity with Epigraph Lifting","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}