{"total":133,"rows":[{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114,"area":null},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2106.08320","title":"Self-Supervised Learning with Kernel Dependence Maximization","created":"2021-06-15","cited_by_count":77,"area":null},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76,"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":"2209.11883","title":"Hebbian Deep Learning Without Feedback","created":"2022-09-23","cited_by_count":61,"area":null},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"area":null},{"id":"2506.05233","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","created":"2025-06-05","cited_by_count":47,"area":null},{"id":"2303.05251","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","created":"2023-03-09","cited_by_count":43,"area":null},{"id":"2301.01452","title":"The Predictive Forward-Forward Algorithm","created":"2023-01-04","cited_by_count":35,"area":null},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32,"area":null},{"id":"2306.06968","title":"Can Forward Gradient Match Backpropagation?","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2204.01723","title":"Signal Propagation: A Framework for Learning and Inference In a Forward Pass","created":"2022-04-04","cited_by_count":24,"area":null},{"id":"2103.04689","title":"Reverse Differentiation via Predictive Coding","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2106.01288","title":"Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence","created":"2021-06-02","cited_by_count":21,"area":null},{"id":"2106.01177","title":"Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck","created":"2021-06-02","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":"2402.07011","title":"FedImpro: Measuring and Improving Client Update in Federated Learning","created":"2024-02-10","cited_by_count":15,"area":null},{"id":"2103.03725","title":"Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks","created":"2021-03-05","cited_by_count":14,"area":null},{"id":"2106.08453","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2106.13031","title":"Towards Biologically Plausible Convolutional Networks","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2302.05440","title":"Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2306.05037","title":"Normalization-Equivariant Neural Networks with Application to Image Denoising","created":"2023-06-08","cited_by_count":11,"area":null},{"id":"2310.11952","title":"Recasting Continual Learning as Sequence Modeling","created":"2023-10-18","cited_by_count":11,"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":"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":"2402.17318","title":"Scaling Supervised Local Learning with Augmented Auxiliary Networks","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2112.13165","title":"Semantic Clustering based Deduction Learning for Image Recognition and Classification","created":"2021-12-25","cited_by_count":8,"area":null},{"id":"2306.02149","title":"A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions","created":"2023-06-03","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":"2212.07282","title":"Low-Variance Forward Gradients using Direct Feedback Alignment and Momentum","created":"2022-12-14","cited_by_count":7,"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":"2101.03419","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":"2102.10557","title":"Contrastive Self-supervised Neural Architecture Search","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2106.08318","title":"Gradient Forward-Propagation for Large-Scale Temporal Video Modelling","created":"2021-06-15","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":"2201.07210","title":"Efficient Training of Spiking Neural Networks with Temporally-Truncated Local Backpropagation through Time","created":"2021-12-13","cited_by_count":3,"area":null},{"id":"2304.13372","title":"Feed-Forward Optimization With Delayed Feedback for Neural Network Training","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2312.05642","title":"Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering Approach","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2312.13311","title":"Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks","created":"2023-12-20","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":"2404.05241","title":"LightFF: Lightweight Inference for Forward-Forward Algorithm","created":"2024-04-08","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":"2412.02482","title":"What should a neuron aim for? Designing local objective functions based on information theory","created":"2024-12-03","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":"2101.06848","title":"Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations","created":"2021-01-18","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":"2206.01820","title":"A Robust Backpropagation-Free Framework for Images","created":"2022-06-03","cited_by_count":2,"area":null},{"id":"2310.09952","title":"Seeking Next Layer Neurons' Attention for Error-Backpropagation-Like Training in a Multi-Agent Network Framework","created":"2023-10-15","cited_by_count":2,"area":null},{"id":"2401.08603","title":"Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning","created":"2023-11-22","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":"2501.16476","title":"Closed-Form Feedback-Free Learning with Forward Projection","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2504.15724","title":"Collaborative Split Federated Learning with Parallel Training and Aggregation","created":"2025-04-22","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":"2104.11604","title":"Learning in Deep Neural Networks Using a Biologically Inspired Optimizer","created":"2021-04-23","cited_by_count":1,"area":null},{"id":"2105.09590","title":"Intra-Model Collaborative Learning of Neural Networks","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2110.11551","title":"Signature-Graph Networks","created":"2021-10-22","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":"2208.00821","title":"Locally Supervised Learning with Periodic Global Guidance","created":"2022-08-01","cited_by_count":1,"area":null},{"id":"2209.06862","title":"Deep learning in a bilateral brain with hemispheric specialization","created":"2022-09-09","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":"2211.01236","title":"Isometric Representations in Neural Networks Improve Robustness","created":"2022-11-02","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":"2401.11694","title":"Parametric Matrix Models","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2402.03332","title":"Cyclic Neural Network","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2407.11698","title":"NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2409.07202","title":"Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained blocks","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2412.00119","title":"Training Multi-Layer Binary Neural Networks With Local Binary Error Signals","created":"2024-11-28","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":"2506.18193","title":"DeInfoReg: A Decoupled Learning Framework for Better Training Throughput","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2506.19693","title":"ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping","created":"2025-06-24","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":"2605.15622","title":"Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2607.18574","title":"Conditioned Direct Feedback Alignment via Activity and Error Geometry","created":"2026-07-20","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":"2106.06998","title":"XConv: Low-memory stochastic backpropagation for convolutional layers","created":"2021-06-13","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}],"next_cursor":"100"}