{"total":44,"rows":[{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49,"area":null},{"id":"2103.14021","title":"Orthogonal Projection Loss","created":"2021-03-25","cited_by_count":44,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"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":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2201.12250","title":"Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2209.07509","title":"Random initialisations performing above chance and how to find them","created":"2022-09-15","cited_by_count":23,"area":null},{"id":"2304.01434","title":"VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2202.10226","title":"Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation","created":"2022-02-14","cited_by_count":14,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2109.14158","title":"Second-Order Neural ODE Optimizer","created":"2021-09-29","cited_by_count":11,"area":null},{"id":"2106.04413","title":"Stochastic Whitening Batch Normalization","created":"2021-06-03","cited_by_count":9,"area":null},{"id":"2106.03947","title":"TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion","created":"2021-06-07","cited_by_count":7,"area":null},{"id":"2203.10778","title":"Delving into the Estimation Shift of Batch Normalization in a Network","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2405.02385","title":"Efficient Deep Learning with Decorrelated Backpropagation","created":"2024-05-03","cited_by_count":7,"area":null},{"id":"2407.10780","title":"Correlations Are Ruining Your Gradient Descent","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2410.15143","title":"Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2401.17401","title":"Step-size Optimization for Continual Learning","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2405.08967","title":"Gradient-Free Training of Recurrent Neural Networks using Random Perturbations","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2410.22568","title":"Fast Deep Hedging with Second-Order Optimization","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2602.19799","title":"Path-conditioned training: a principled way to rescale ReLU neural networks","created":"2026-02-23","cited_by_count":6,"area":null},{"id":"2108.01110","title":"Batch Normalization Preconditioning for Neural Network Training","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2205.08385","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2307.04343","title":"Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2108.10629","title":"Improving Generalization of Batch Whitening by Convolutional Unit Optimization","created":"2021-08-24","cited_by_count":3,"area":null},{"id":"2103.16634","title":"Exploiting Invariance in Training Deep Neural Networks","created":"2021-03-30","cited_by_count":2,"area":null},{"id":"2110.05324","title":"Learnable Adaptive Cosine Estimator (LACE) for Image Classification","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2310.00965","title":"Node Perturbation Can Effectively Train Multi-Layer Neural Networks","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2506.22479","title":"Hindsight-Guided Momentum (HGM) Optimizer: An Approach to Adaptive Learning Rate","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2103.07554","title":"A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training","created":"2021-03-12","cited_by_count":1,"area":null},{"id":"2104.01061","title":"Information Geometry and Classical Cram\\'{e}r-Rao Type Inequalities","created":"2021-04-02","cited_by_count":1,"area":null},{"id":"2206.02454","title":"What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective","created":"2022-06-06","cited_by_count":1,"area":null},{"id":"2510.25262","title":"IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2601.03162","title":"On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2607.01455","title":"Ember: A Kilobyte-State Optimizer for Token Interfaces","created":"2026-07-01","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":"2204.10972","title":"GRM: Gradient Rectification Module for Visual Place Retrieval","created":"2022-04-23","cited_by_count":0,"area":null},{"id":"2310.12298","title":"Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2510.14657","title":"Decorrelation Speeds Up Vision Transformers","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.18812","title":"A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.03610","title":"Riemannian Optimization in Modular Systems","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.20898","title":"Natural Gradient Descent for Online Continual Learning","created":"2026-03-21","cited_by_count":0,"area":null}],"next_cursor":null}