{"total":150,"rows":[{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170,"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":"2410.18164","title":"TabDPT: Scaling Tabular Foundation Models on Real Data","created":"2024-10-23","cited_by_count":113,"area":null},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73,"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":"2506.07918","title":"CausalPFN: Amortized Causal Effect Estimation via In-Context Learning","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"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":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2405.18144","title":"4-bit Shampoo for Memory-Efficient Network Training","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2502.00631","title":"MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2407.20750","title":"JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources","created":"2024-07-30","cited_by_count":15,"area":null},{"id":"2411.07061","title":"General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2507.08972","title":"Simulating Three-dimensional Turbulence with Physics-informed Neural Networks","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2603.03805","title":"Relational In-Context Learning via Synthetic Pre-training with Structural Prior","created":"2026-03-04","cited_by_count":14,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2411.01803","title":"Gradient Methods with Online Scaling","created":"2024-11-04","cited_by_count":11,"area":null},{"id":"2503.19466","title":"A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction","created":"2025-03-25","cited_by_count":11,"area":null},{"id":"2407.04358","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2602.20223","title":"MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2505.21910","title":"Taming Transformer Without Using Learning Rate Warmup","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2507.09846","title":"Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training","created":"2025-07-14","cited_by_count":9,"area":null},{"id":"2509.10439","title":"Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.22397","title":"GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2605.19095","title":"ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2508.00643","title":"Light-Weight Diffusion Multiplier and Uncertainty Quantification for Fourier Neural Operators","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2602.13498","title":"TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2502.11229","title":"Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2504.06920","title":"S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2505.16791","title":"Cohort-Based Active Modality Acquisition","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2512.22991","title":"Fusion or Confusion? Multimodal Complexity Is Not All You Need","created":"2025-12-28","cited_by_count":5,"area":null},{"id":"2602.05813","title":"Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers","created":"2026-02-05","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":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2411.15872","title":"Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics","created":"2024-11-24","cited_by_count":4,"area":null},{"id":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2503.10103","title":"Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation","created":"2025-03-13","cited_by_count":4,"area":null},{"id":"2507.20708","title":"Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2509.00116","title":"Meta-learning ecological priors from large language models explains human learning and decision making","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2510.09768","title":"Scaling Laws and Symmetry, Evidence from Neural Force Fields","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2604.13870","title":"Gradient Descent's Last Iterate is Often (slightly) Suboptimal","created":"2026-04-15","cited_by_count":4,"area":null},{"id":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2607.22444","title":"Hyperball May Not Be a Free Lunch","created":"2026-07-24","cited_by_count":4,"area":null},{"id":"2502.21320","title":"TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2503.13057","title":"MaskSDM with Shapley values to improve flexibility, robustness, and explainability in species distribution modeling","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2506.06606","title":"Stacey: Promoting Stochastic Steepest Descent via Accelerated $\\ell_p$-Smooth Nonconvex Optimization","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2510.14009","title":"Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2512.23930","title":"Assessing generative modeling approaches for free energy estimates in condensed matter","created":"2025-12-30","cited_by_count":3,"area":null},{"id":"2605.11172","title":"Optimistic Dual Averaging Unifies Modern Optimizers","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.23061","title":"Anytime Training with Schedule-Free Spectral Optimization","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.17516","title":"FoundCause: Causal Discovery with Latent Confounders from Observational Data","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2410.19426","title":"Analyzing Generative Models by Manifold Entropic Metrics","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2412.19444","title":"Towards Simple and Provable Parameter-Free Adaptive Gradient Methods","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2502.01084","title":"Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2502.17397","title":"Robust Confinement State Classification with Uncertainty Quantification through Ensembled Data-Driven Methods","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2504.17710","title":"Plasma State Monitoring and Disruption Characterization using Multimodal VAEs","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2505.21651","title":"AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2505.24005","title":"How far away are truly hyperparameter-free learning algorithms?","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.20355","title":"Practical insights on the effect of different encodings, ans\\\"atze and measurements in quantum and hybrid convolutional neural networks","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2506.23382","title":"SIEDD: Shared-Implicit Encoder with Discrete Decoders","created":"2025-06-29","cited_by_count":2,"area":null},{"id":"2510.07473","title":"metabeta -- A fast neural model for Bayesian mixed-effects regression","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2511.07767","title":"Taking the Road Less Scheduled with Adaptive Polyak Steps","created":"2025-11-11","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":"2602.23128","title":"Bound to Disagree: Generalization Bounds via Certifiable Surrogates","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2604.05834","title":"Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.00650","title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.15268","title":"When to use what Schatten-$p$ norm in deep learning?","created":"2026-06-13","cited_by_count":2,"area":null},{"id":"2606.19179","title":"Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2609.31862","title":"Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks","created":"2026-09-25","cited_by_count":2,"area":null},{"id":"2412.10351","title":"VibrantVS: A high-resolution multi-task transformer for forest canopy height estimation","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2412.17082","title":"MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2505.13397","title":"Learning by solving differential equations","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.22085","title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.10572","title":"Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2507.02576","title":"Parametric shape models for vessels learned from segmentations via differentiable voxelization","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.23256","title":"EMedNeXt: An Enhanced Brain Tumor Segmentation Framework for Sub-Saharan Africa using MedNeXt V2 with Deep Supervision","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.06743","title":"Analysis of Schedule-Free Nonconvex Optimization","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.05084","title":"Recurrent State Encoders for Efficient Neural Combinatorial Optimization","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2509.05811","title":"Simple Optimizers for Convex Aligned Multi-Objective Optimization","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2510.06204","title":"Modulation Discovery with Differentiable Digital Signal Processing","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2511.06597","title":"Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2603.26954","title":"High dimensional theory of two-phase optimizers","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2606.21433","title":"Central limit theorem for the averaged Adam optimizer","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2606.25086","title":"Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2609.04577","title":"Optimizer Memory Schedules for Outscaling the Overtraining Axis","created":"2026-09-04","cited_by_count":1,"area":null}],"next_cursor":"100"}