{"total":19,"rows":[{"id":"2111.05177","title":"On Training Implicit Models","created":"2021-11-09","cited_by_count":75,"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":"2208.08772","title":"Lifted Bregman Training of Neural Networks","created":"2022-08-18","cited_by_count":10,"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":"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":"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":"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":"2401.11694","title":"Parametric Matrix Models","created":"2024-01-22","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":"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":"2108.00400","title":"Transformer-Encoder-GRU (T-E-GRU) for Chinese Sentiment Analysis on Chinese Comment Text","created":"2021-08-01","cited_by_count":0,"area":null},{"id":"2310.15334","title":"ADMM Algorithms for Residual Network Training: Convergence Analysis and Parallel Implementation","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2408.08742","title":"A lifted Bregman strategy for training unfolded proximal neural network Gaussian denoisers","created":"2024-08-16","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}