PaperScope
LIVE · 2026-09-11 05:40 UTC

gradient descent 6 papers this week · +40% WoW

papers mentioning "gradient descent" in title/abstract · 30d window

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1AdamX: Cosine similarity meets gradient descentFrancisco Caldas, Ruben Belo, Cláudia Soarescs.LG2026-09-10
2Generalization Analysis of Distributed Kernel-based Robust Gradient Descent AlgorithmsJun-Yi Meng, Zheng-Chu Guo, Yuan Maostat.ML2026-09-10
3Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and SymmetryMo Zhou, Weihang Xu, Simon S. Du +1cs.LG2026-09-09
#4Adversarial Training for Tabular Credit Scoring: A Multi-Attack Robustness Evaluation in P2P LendingGijs A. F. Niewzwaag, Marijn G. S. Veth, Manuele Massei +1cs.LG2026-09-09
#5Online Inverse Integer Linear Optimization via Small-Gradient Skipping: Constant Regret and Finite MistakesAkira Kitaokacs.LG2026-09-09
#6Settling: Equilibrium Inference for Non-Convex Validity SetsLyes Saad Saoudcs.LG2026-09-09
#7Exact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-LeaderAshkan Soleymani, Gabriele Farina, Patrick Jailletcs.LG2026-09-08
#8Silver Rate Is (Almost) Optimal for Gradient Descent AccelerationYuhan Ye, Kaizhao Liumath.OC2026-09-08
#9The Exact Time-Uniform Rate Frontier for Stochastic Gradient Descent on Smooth Convex ObjectivesRuijie Li, Kang Chen, Tianyu Wangmath.OC2026-09-08
#10Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient DescentQuang-Duy Tran, Trung Le, Bao Duong +2cs.LG2026-09-08
#11Speed Limit for Information Acquisition in Stochastic Learning DynamicsShuta Kobayashi, Andreas Dechantcond-mat.stat-mech2026-09-08
#12Sparse Data Augmentation for Optimization with Provable GuaranteesBehrooz Tahmasebi, Melanie Webercs.LG2026-09-08
#13A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight DecayYuqing Wang, Ioannis G. Kevrekidis, Mikhail Belkincs.LG2026-09-07
#14Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federated Learning SettingChayun Kongtongvattanacs.CV2026-09-06
#15Stochastic Nonconvex Bilevel Optimization: Improved Rates Without Rare-Visit AssumptionDaniel Cortild, Mathias Staudigl, Juan Peypouquet +1math.OC2026-09-06
#16Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural NetworksYiming Yingcs.LG2026-09-06
#17Fast Gauss Sums via Flash AttentionNicolaj Rux, Sebastian Neumayercs.LG2026-09-04
#18Centered Permutation Prefixes for SGD with Random Reshuffling: Sharp Rates, Hölder Geometry, and Composite Proximal ExtensionsJiaxiang Limath.OC2026-09-04
#19High-Dimensional Learning Dynamics of Attention-Indexed ModelsYizhou Xu, Margarita Sagitova, Lenka Zdeborová +1cs.LG2026-09-03
#20Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step SizeA. Afhamcs.LG2026-09-03
#21Improved Gradient Descent Lower Bounds Beyond NesterovYuhan Ye, Kaizhao Liumath.OC2026-09-02
#22Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale InvarianceSai Niranjan Ramachandran, Suvrit Sracs.LG2026-09-02
#23Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural NetworksOsvaldo M Velarde, Lucas C Parra, Alireza Hashemi +1cs.LG2026-09-01
#24Rethinking Learnability in Offline Data-driven OptimizationChao Qian, Chen-Guang Wang, Rong-Xi Tan +1cs.LG2026-09-01
#25The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central FlowRaphaël Berthiercs.LG2026-09-01
#26Subspace Levenberg Marquardt Algorithms in Training Neural NetworksM. Duc Hoangcs.LG2026-09-01
#27Operational Regimes in Non-Convex Optimization: A Multiplier-Based TaxonomySeyed Mohsen Kazemi, Ali Movaghar, Shaahin hessabimath.OC2026-08-31
#28Singular Curvature in ReLU Training:Differentiation and the Gradient-Flow Limit Need Not CommuteXiaoyang Li, Runni Zhoucs.LG2026-08-31
#29Reciprocity Separates Gradient Flow from Rotation in Conservative Physical LearningRuiwu Niu, Xiaowen Bi, Michaël Antonie van Wykcs.LG2026-08-31
#30Generalization as a robust performance property of learning-enabled dynamical systemsFilippo Fabianieess.SY2026-08-31
#31Convergence rates for the RMSprop optimizer with full control of the hyperparametersSteffen Dereich, Arnulf Jentzencs.LG2026-08-31
#32REAL-Q: E2E LLM Quantization via Dynamic Gradient DescentQian Zhang, Yaoming Li, Zhewen Tan +9cs.LG2026-08-30
#33Quantitative Target Convergence and Uniform-in-Time Propagation of Chaos for Langevin-Regularized SVGDSayan Banerjee, Dohyeon Kimstat.ML2026-08-28
#34Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential EquationsYuehao Song, Zhong Chen, Lihui Cen +2math.NA2026-08-27
#35Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping RulesLiviu Aolaritei, Lucas Lévy, Francis Bach +1cs.LG2026-08-26
#36A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-normDuy Hoang, Bastien Berret, Olivier Bruneau +1cs.LG2026-08-25
#37Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual LearningOwen Skriloffmath.OC2026-08-24
#38Machine Learning Assisted Inverse Design of Pixelated mmWave Patch AntennasNadeem Rather, Holger Claussen, Lester Hoeess.SP2026-08-24
#39SGHA: A Single-Loop Fully First-Order Algorithm for Nonconvex-Strongly-Convex Bilevel OptimizationZhihao Gu, Qilong Wu, Junchi Yangmath.OC2026-08-24
#40One Inverse Step is a Convex Program: Bayes-Limit Calibration of Diffusion InversionGordei Verbiistat.ML2026-08-24
#41Stochastic gradient descent with initial regularizationNabil Kahalécs.LG2026-08-24
#42Where Cognition Lives: Dissecting Emergent from Computed Function in a Minimal Complete Cognitive ArchitectureFrancisco M. Arrabal-Campos, Francisco G. Montoya, Alfredo Alcayde +1cs.AI2026-08-23
#43Variational Structure at the Edge of StabilityEric Regiscs.LG2026-08-21
#44Kähler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifoldAndrew Gracykcs.LG2026-08-20
#45Quantum Tensor Network Learning with DMRGGustav J L Jäger, Martin B Plenio, Hans-Martin Rieserquant-ph2026-08-19
#46The Road Taken: The Role of Optimizers at the Edge of StabilityJaerin Lee, Kyoung Mu Leecs.LG2026-08-19
#47Causal Discovery in Equal Variance Linear Gaussian DAGs via SURE-Tuned Ridge RegressionSambit Mishra, Urbashi Mitracs.LG2026-08-17
#48Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision SystemAlam Noor, Luis Almeida, Kai Li +3cs.CV2026-08-17
#49Differentiable Voxelization of Surface RepresentationsTobias Djuren, Ugo Finnendahl, Markus Worchel +2cs.GR2026-08-16
#50Spectral Saliency for Machine UnlearningCedar Site Bai, Amber Yijia Zheng, Raymond A. Yeh +1cs.LG2026-08-16

all trends · matching is case-insensitive substring after tokenization