{"total":728,"rows":[{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"area":null},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"area":null},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2304.13960","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","created":"2023-04-27","cited_by_count":114,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106,"area":null},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2403.05175","title":"Continual Learning and Catastrophic Forgetting","created":"2024-03-08","cited_by_count":77,"area":null},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2111.04726","title":"Estimating High Order Gradients of the Data Distribution by Denoising","created":"2021-11-08","cited_by_count":64,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62,"area":null},{"id":"2206.08720","title":"Fast Finite Width Neural Tangent Kernel","created":"2022-06-17","cited_by_count":62,"area":null},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"area":null},{"id":"2202.11678","title":"Bayesian Model Selection, the Marginal Likelihood, and Generalization","created":"2022-02-23","cited_by_count":57,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2109.11369","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54,"area":null},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"area":null},{"id":"2110.01765","title":"Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping","created":"2021-10-05","cited_by_count":52,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2211.13672","title":"A Self-Attention Ansatz for Ab-initio Quantum Chemistry","created":"2022-11-24","cited_by_count":49,"area":null},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"id":"2106.08085","title":"Natural continual learning: success is a journey, not (just) a destination","created":"2021-06-15","cited_by_count":46,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2306.01244","title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2308.14991","title":"Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence","created":"2023-08-29","cited_by_count":43,"area":null},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42,"area":null},{"id":"2102.00084","title":"A linearized framework and a new benchmark for model selection for fine-tuning","created":"2021-01-29","cited_by_count":41,"area":null},{"id":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","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":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"area":null},{"id":"2407.19115","title":"Towards Scalable and Stable Parallelization of Nonlinear RNNs","created":"2024-07-26","cited_by_count":38,"area":null},{"id":"2110.05064","title":"Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions","created":"2021-10-11","cited_by_count":37,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34,"area":null},{"id":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2102.12567","title":"Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks","created":"2021-02-24","cited_by_count":32,"area":null},{"id":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32,"area":null},{"id":"2410.20625","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","created":"2024-10-27","cited_by_count":32,"area":null},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"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":"2405.12915","title":"G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation","created":"2024-05-21","cited_by_count":30,"area":null},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2106.07887","title":"Credit Assignment in Neural Networks through Deep Feedback Control","created":"2021-06-15","cited_by_count":29,"area":null},{"id":"2206.08900","title":"Adapting the Linearised Laplace Model Evidence for Modern Deep Learning","created":"2022-06-17","cited_by_count":29,"area":null},{"id":"2208.12590","title":"Ab-initio quantum chemistry with neural-network wavefunctions","created":"2022-08-26","cited_by_count":29,"area":null},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28,"area":null},{"id":"2106.10185","title":"NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights","created":"2021-06-18","cited_by_count":28,"area":null},{"id":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28,"area":null},{"id":"2210.12642","title":"Accelerated Linearized Laplace Approximation for Bayesian Deep Learning","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2302.04168","title":"Generalizing Neural Wave Functions","created":"2023-02-08","cited_by_count":28,"area":null},{"id":"2205.09438","title":"Gold-standard solutions to the Schr\\\"odinger equation using deep learning: How much physics do we need?","created":"2022-05-19","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2401.10190","title":"A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions","created":"2024-01-18","cited_by_count":26,"area":null},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25,"area":null},{"id":"2205.10637","title":"Symmetry Teleportation for Accelerated Optimization","created":"2022-05-21","cited_by_count":25,"area":null},{"id":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","cited_by_count":25,"area":null},{"id":"2105.08351","title":"Solving the electronic Schr\\\"odinger equation for multiple nuclear geometries with weight-sharing deep neural networks","created":"2021-05-18","cited_by_count":24,"area":null},{"id":"2106.02925","title":"Tensor Normal Training for Deep Learning Models","created":"2021-06-05","cited_by_count":24,"area":null},{"id":"2211.14133","title":"PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2211.14406","title":"Exploring Temporal Information Dynamics in Spiking Neural Networks","created":"2022-11-26","cited_by_count":24,"area":null},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23,"area":null},{"id":"2106.05367","title":"Pulling back information geometry","created":"2021-06-09","cited_by_count":23,"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":"2305.19535","title":"Low-rank extended Kalman filtering for online learning of neural networks from streaming data","created":"2023-05-31","cited_by_count":23,"area":null},{"id":"2310.06131","title":"Learning Layer-wise Equivariances Automatically using Gradients","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2107.04205","title":"On the Variance of the Fisher Information for Deep Learning","created":"2021-07-09","cited_by_count":22,"area":null},{"id":"2112.02089","title":"Regularized Newton Method with Global $O(1/k^2)$ Convergence","created":"2021-12-03","cited_by_count":22,"area":null},{"id":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22,"area":null},{"id":"2310.00339","title":"FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation","created":"2023-09-30","cited_by_count":22,"area":null}],"next_cursor":"100"}