{"total":115,"rows":[{"id":"2207.08799","title":"Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit","created":"2022-07-18","cited_by_count":187,"area":null},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2104.14380","title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","created":"2021-04-29","cited_by_count":93,"area":null},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87,"area":null},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2101.10832","title":"Revisiting Locally Supervised Learning: an Alternative to End-to-end Training","created":"2021-01-26","cited_by_count":71,"area":null},{"id":"2210.03310","title":"Scaling Forward Gradient With Local Losses","created":"2022-10-07","cited_by_count":65,"area":null},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2202.01331","title":"Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions","created":"2022-02-02","cited_by_count":31,"area":null},{"id":"2110.11995","title":"PhotoWCT$^2$: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residuals","created":"2021-10-22","cited_by_count":30,"area":null},{"id":"2404.02827","title":"BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2306.06968","title":"Can Forward Gradient Match Backpropagation?","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2302.01647","title":"Blockwise Self-Supervised Learning at Scale","created":"2023-02-03","cited_by_count":22,"area":null},{"id":"2509.26238","title":"Beyond Linear Probes: Dynamic Safety Monitoring for Language Models","created":"2025-09-30","cited_by_count":16,"area":"safety"},{"id":"2201.01965","title":"Efficient Global Optimization of Two-Layer ReLU Networks: Quadratic-Time Algorithms and Adversarial Training","created":"2022-01-06","cited_by_count":15,"area":null},{"id":"2207.08267","title":"Gigapixel Whole-Slide Images Classification using Locally Supervised Learning","created":"2022-07-17","cited_by_count":15,"area":null},{"id":"2101.02429","title":"Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully Polynomial-Time","created":"2021-01-07","cited_by_count":14,"area":null},{"id":"2110.09548","title":"Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks","created":"2021-10-18","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":"2311.18130","title":"The Trifecta: Three simple techniques for training deeper Forward-Forward networks","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2506.14202","title":"DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2104.04657","title":"Meta-Learning Bidirectional Update Rules","created":"2021-04-10","cited_by_count":10,"area":null},{"id":"2310.07194","title":"Boosting Learning for LDPC Codes to Improve the Error-Floor Performance","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2407.05623","title":"Momentum Auxiliary Network for Supervised Local Learning","created":"2024-07-08","cited_by_count":10,"area":null},{"id":"2212.11115","title":"What Makes for Good Tokenizers in Vision Transformer?","created":"2022-12-21","cited_by_count":9,"area":null},{"id":"2402.17318","title":"Scaling Supervised Local Learning with Augmented Auxiliary Networks","created":"2024-02-27","cited_by_count":9,"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":"2101.07528","title":"The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods","created":"2021-01-19","cited_by_count":8,"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":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2503.24322","title":"NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2106.06401","title":"Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning","created":"2021-06-11","cited_by_count":6,"area":null},{"id":"2109.15089","title":"Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks","created":"2021-09-30","cited_by_count":6,"area":null},{"id":"2305.14974","title":"Block-local learning with probabilistic latent representations","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2406.00446","title":"Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2406.02052","title":"PETRA: Parallel End-to-end Training with Reversible Architectures","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2101.02338","title":"Max-Affine Spline Insights Into Deep Network Pruning","created":"2021-01-07","cited_by_count":5,"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":"2306.10486","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","created":"2023-06-18","cited_by_count":5,"area":null},{"id":"2405.15868","title":"LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2406.16633","title":"MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2407.05638","title":"HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2210.14593","title":"Scaling Laws Beyond Backpropagation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2212.14215","title":"Local Learning on Transformers via Feature Reconstruction","created":"2022-12-29","cited_by_count":4,"area":null},{"id":"2301.07635","title":"Local Learning with Neuron Groups","created":"2023-01-18","cited_by_count":4,"area":null},{"id":"2309.17357","title":"Module-wise Training of Neural Networks via the Minimizing Movement Scheme","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2406.05222","title":"Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2409.03306","title":"Towards training digitally-tied analog blocks via hybrid gradient computation","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2106.05554","title":"Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement","created":"2021-06-10","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":"2207.08393","title":"GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction","created":"2022-07-18","cited_by_count":3,"area":null},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2304.14831","title":"Earning Extra Performance from Restrictive Feedbacks","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2401.03104","title":"When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks","created":"2024-01-06","cited_by_count":3,"area":null},{"id":"2402.04958","title":"Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2406.15125","title":"Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2409.19561","title":"Unifying back-propagation and forward-forward algorithms through model predictive control","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2507.16279","title":"MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2509.12394","title":"Adaptive Spatial Goodness Encoding: Advancing and Scaling Forward-Forward Learning Without Backpropagation","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2605.00082","title":"Hyperspherical Forward-Forward with Prototypical Representations","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2106.13955","title":"Autonomous Deep Quality Monitoring in Streaming Environments","created":"2021-06-26","cited_by_count":2,"area":null},{"id":"2112.05387","title":"Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks","created":"2021-12-10","cited_by_count":2,"area":null},{"id":"2202.01210","title":"Deep Layer-wise Networks Have Closed-Form Weights","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2211.06860","title":"An Adaptive and Stability-Promoting Layerwise Training Approach for Sparse Deep Neural Network Architecture","created":"2022-11-13","cited_by_count":2,"area":null},{"id":"2411.06848","title":"Generative Feature Training of Thin 2-Layer Networks","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2601.09076","title":"Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2102.04697","title":"Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2111.13187","title":"Information Bottleneck-Based Hebbian Learning Rule Naturally Ties Working Memory and Synaptic Updates","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2203.05417","title":"Deep Regression Ensembles","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2205.07141","title":"BackLink: Supervised Local Training with Backward Links","created":"2022-05-14","cited_by_count":1,"area":null},{"id":"2205.14056","title":"Dual Convexified Convolutional Neural Networks","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2208.00821","title":"Locally Supervised Learning with Periodic Global Guidance","created":"2022-08-01","cited_by_count":1,"area":null},{"id":"2210.00949","title":"Block-wise Training of Residual Networks via the Minimizing Movement Scheme","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2212.12866","title":"QuickNets: Saving Training and Preventing Overconfidence in Early-Exit Neural Architectures","created":"2022-12-25","cited_by_count":1,"area":null},{"id":"2310.07885","title":"Leader-Follower Neural Networks with Local Error Signals Inspired by Complex Collectives","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2311.17218","title":"BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2312.11436","title":"Layerwise complexity-matched learning yields an improved model of cortical area V2","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2402.14139","title":"NeuroFlux: Memory-Efficient CNN Training Using Adaptive Local Learning","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2403.03871","title":"Decoupled Vertical Federated Learning for Practical Training on Vertically Partitioned Data","created":"2024-03-06","cited_by_count":1,"area":null},{"id":"2403.11004","title":"Forward Learning of Graph Neural Networks","created":"2024-03-16","cited_by_count":1,"area":null},{"id":"2406.17954","title":"Why Line Search when you can Plane Search? SO-Friendly Neural Networks allow Per-Iteration Optimization of Learning and Momentum Rates for Every Layer","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2505.05181","title":"Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2510.25594","title":"Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2602.09569","title":"Training deep physical neural networks with local physical information bottleneck","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2106.05569","title":"Front Contribution instead of Back Propagation","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2106.05875","title":"Interferometric Graph Transform for Community Labeling","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2110.10379","title":"Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2206.02006","title":"Combinatorial optimization for low bit-width neural networks","created":"2022-06-04","cited_by_count":0,"area":null},{"id":"2209.03839","title":"FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2308.02427","title":"Unlocking the Potential of Similarity Matching: Scalability, Supervision and Pre-training","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2312.07636","title":"Go beyond End-to-End Training: Boosting Greedy Local Learning with Context Supply","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2510.00883","title":"GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.06649","title":"Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2510.27651","title":"Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.09040","title":"Depth-Wise Representation Development Under Blockwise Self-Supervised Learning for Video Vision Transformers","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.19261","title":"Decoupled Split Learning via Auxiliary Loss","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.00951","title":"When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2606.03209","title":"DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":"100"}