{"total":99,"rows":[{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2109.08215","title":"Pre-trained Gaussian Processes for Bayesian Optimization","created":"2021-09-16","cited_by_count":63,"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":"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":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2110.04369","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","created":"2021-10-08","cited_by_count":40,"area":null},{"id":"2502.15015","title":"Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition","created":"2025-02-20","cited_by_count":32,"area":null},{"id":"2101.11075","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","created":"2021-01-26","cited_by_count":28,"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":"2106.02925","title":"Tensor Normal Training for Deep Learning Models","created":"2021-06-05","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":"2212.09360","title":"AI Security for Geoscience and Remote Sensing: Challenges and Future Trends","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2102.03034","title":"Hyperparameter Optimization Is Deceiving Us, and How to Stop It","created":"2021-02-05","cited_by_count":20,"area":null},{"id":"2102.06356","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2103.06595","title":"Bump Hunting in Latent Space","created":"2021-03-11","cited_by_count":19,"area":null},{"id":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2303.07127","title":"Improving physics-informed neural networks with meta-learned optimization","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2208.13219","title":"Visualizing high-dimensional loss landscapes with Hessian directions","created":"2022-08-28","cited_by_count":16,"area":null},{"id":"2402.07745","title":"Predictive Churn with the Set of Good Models","created":"2024-02-12","cited_by_count":15,"area":null},{"id":"2305.00224","title":"An Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-based Gradients","created":"2023-04-27","cited_by_count":14,"area":null},{"id":"2111.07971","title":"Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2102.08431","title":"Complex Momentum for Optimization in Games","created":"2021-02-16","cited_by_count":11,"area":null},{"id":"2206.05985","title":"Modeling the Machine Learning Multiverse","created":"2022-06-13","cited_by_count":11,"area":null},{"id":"2501.06572","title":"Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities","created":"2025-01-11","cited_by_count":11,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2206.11120","title":"Near-optimal control of dynamical systems with neural ordinary differential equations","created":"2022-06-22","cited_by_count":9,"area":null},{"id":"2202.04124","title":"A Mini-Block Fisher Method for Deep Neural Networks","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2203.01400","title":"Adaptive Gradient Methods with Local Guarantees","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2211.12386","title":"A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms","created":"2022-11-22","cited_by_count":8,"area":null},{"id":"2303.14604","title":"Green Federated Learning","created":"2023-03-26","cited_by_count":8,"area":null},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8,"area":null},{"id":"2412.17227","title":"Brain-to-Text Benchmark '24: Lessons Learned","created":"2024-12-23","cited_by_count":8,"area":null},{"id":"2104.00606","title":"Model Selection's Disparate Impact in Real-World Deep Learning Applications","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2310.20673","title":"Balancing Act: Constraining Disparate Impact in Sparse Models","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2406.00367","title":"RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis","created":"2024-06-01","cited_by_count":7,"area":null},{"id":"2102.06737","title":"Kronecker-factored Quasi-Newton Methods for Deep Learning","created":"2021-02-12","cited_by_count":6,"area":null},{"id":"2102.11537","title":"Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2107.12013","title":"A Shallow Ritz Method for Elliptic Problems with Singular Sources","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2107.12460","title":"Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2409.15264","title":"UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework","created":"2024-09-23","cited_by_count":6,"area":null},{"id":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2112.09568","title":"Nearest neighbor search with compact codes: A decoder perspective","created":"2021-12-17","cited_by_count":5,"area":null},{"id":"2210.16400","title":"Flatter, faster: scaling momentum for optimal speedup of SGD","created":"2022-10-28","cited_by_count":5,"area":null},{"id":"2604.15297","title":"Benchmarking Optimizers for MLPs in Tabular Deep Learning","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2403.13704","title":"Improving the Adaptive Moment Estimation (ADAM) stochastic optimizer through an Implicit-Explicit (IMEX) time-stepping approach","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2411.05296","title":"On Training of Kolmogorov-Arnold Networks","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2501.12670","title":"Celo: Training Versatile Learned Optimizers on a Compute Diet","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2510.26997","title":"Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2210.04319","title":"Dissecting adaptive methods in GANs","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2211.08583","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2408.06018","title":"Uncertainty-Informed Volume Visualization using Implicit Neural Representation","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2408.09310","title":"Narrowing the Focus: Learned Optimizers for Pretrained Models","created":"2024-08-17","cited_by_count":3,"area":null},{"id":"2410.14158","title":"A Mirror Descent Perspective of Smoothed Sign Descent","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2602.00334","title":"Adaptive Momentum and Nonlinear Damping for Neural Network Training","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2107.04695","title":"L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2107.06773","title":"Relational graph convolutional networks for predicting blood-brain barrier penetration of drug molecules","created":"2021-07-04","cited_by_count":2,"area":null},{"id":"2110.14813","title":"Stable Anderson Acceleration for Deep Learning","created":"2021-10-26","cited_by_count":2,"area":null},{"id":"2112.08250","title":"Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2310.18191","title":"Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2406.18545","title":"Visual Analysis of Prediction Uncertainty in Neural Networks for Deep Image Synthesis","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2411.06858","title":"Scientific machine learning in ecological systems: A study on the predator-prey dynamics","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2512.06370","title":"Greedy Alignment Principle for Optimizer Selection","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2101.09192","title":"Gravity Optimizer: a Kinematic Approach on Optimization in Deep Learning","created":"2021-01-22","cited_by_count":1,"area":null},{"id":"2110.14920","title":"Efficient Meta Subspace Optimization","created":"2021-10-28","cited_by_count":1,"area":null},{"id":"2206.12112","title":"Dissecting U-net for Seismic Application: An In-Depth Study on Deep Learning Multiple Removal","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2209.12499","title":"Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2402.06948","title":"Should I try multiple optimizers when fine-tuning pre-trained Transformers for NLP tasks? Should I tune their hyperparameters?","created":"2024-02-10","cited_by_count":1,"area":null},{"id":"2409.11995","title":"Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2506.06815","title":"Path Integral Optimiser: Global Optimisation via Neural Schr\\\"odinger-F\\\"ollmer Diffusion","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2601.07830","title":"Optimal Learning Rate Schedule for Balancing Effort and Performance","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2609.25518","title":"Matryoshka attribution: Learning to attribute language model outputs to representations and weights","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2105.07222","title":"On the Distributional Properties of Adaptive Gradients","created":"2021-05-15","cited_by_count":0,"area":null},{"id":"2105.14625","title":"Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT","created":"2021-05-30","cited_by_count":0,"area":null},{"id":"2108.05839","title":"Logit Attenuating Weight Normalization","created":"2021-08-12","cited_by_count":0,"area":null},{"id":"2111.14056","title":"Towards Robust and Automatic Hyper-Parameter Tunning","created":"2021-11-28","cited_by_count":0,"area":null},{"id":"2207.03577","title":"Automatic Synthesis of Neurons for Recurrent Neural Nets","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2303.03540","title":"Judging Adam: Studying the Performance of Optimization Methods on ML4SE Tasks","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2305.13664","title":"Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2307.09638","title":"Promoting Exploration in Memory-Augmented Adam using Critical Momenta","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2311.11532","title":"Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $\\epsilon$ via Gradient Magnitude Histogram Analysis","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2402.02447","title":"Breaking MLPerf Training: A Case Study on Optimizing BERT","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2402.16546","title":"Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2405.10957","title":"Statistical Mechanics and Artificial Neural Networks: Principles, Models, and Applications","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2502.02385","title":"Achieving Hiding and Smart Anti-Jamming Communication: A Parallel DRL Approach against Moving Reactive Jammer","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2505.21589","title":"Do you see what I see? An Ambiguous Optical Illusion Dataset exposing limitations of Explainable AI","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2506.12944","title":"Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2509.13516","title":"An Analysis of Optimizer Choice on Energy Efficiency and Performance in Neural Network Training","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2602.23219","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2609.25914","title":"AURA: Angular Update Rate Adaptation for training complex-valued neural networks","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.08975","title":"The Best Optimizer Depends on Batch Size","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09425","title":"What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.09835","title":"A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.18695","title":"A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}