NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
583 results for “keyword:"gradient"” in ICLR 2027. 106 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Scaling Gradient Projection for Continual Learning Over Long Task Sequences via Spectral Consolidation▲5103.00
[PDF]Finding Structure Without Fitting Noise: Taking Apart the Small-Table Advantage of Tabular Foundation Models▼4.3k2.00
[PDF]Ideal Paths: Geometric Approximation of Logistic Gradient Descent Trajectories at Large Initialization▲13k2.33
[PDF]EG-Opt: Efficient Learning for Nonlinear Programming via Explicit Gradients from Sample-Calibrated Linear Surrogates▼5.8k2.33
[PDF]WHAT EMPIRICAL TRAINING DYNAMICS DO NOT DETERMINE: RELU HISTORIES AND ROBUST PREDICTION SEPARATION▼1361.33
[PDF]Normalization Couples What the Objective Separates: Representation Selection in Group Composition Networks▲153.33
[PDF]DISTRIBUTED GRADIENT TRACKING ACHIEVING THE OPTIMAL WORST-CASE CONVERGENCE RATE OF CENTRALIZED GRADIENT DESCENT: NECESSARY AND SUFFICIENT CONDITIONS AND BEYOND▲3.0k2.33
[PDF]Finite-Shot Quantum Federated Learning: Trajectory-Dependent Update Discrepancies and Nonconvex Convergence under Proximal Dynamics▼4.3k2.00
[PDF]ScaledGD for Underparameterized Matrix Factorization: Global Convergence and Stepsize Universality▲603.50
[PDF]Query Complexity of Forward-Only Hebbian Learning: Theory and a Native Fit for Diffusion Models▼4.3k2.00
[PDF]IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback▼1.2k1.67
[PDF]Parameter Symmetries Are Not Task Symmetries: Which Invariances Can Weight-Space Learning Afford?▼11k2.33
[PDF]Steering What SGD Learns: Spectral Control of Optimization through Dynamic Data Transformation▼1.2k1.67
[PDF]How Multi-Head Transformers Specialize for In-Context Learning: A Theoretical Analysis of Training Dynamics and Generalization▲2843.00
[PDF]AdvG: A Provably Convergent Actor–Critic Algorithm for Reinforcement Learning in Continuous Time and Space▲5103.00
[PDF]Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise▼1.2k3.00
[PDF]Alignment and Convergence Analyses of Gradient Flow in Two-Layer Convolutional Neural Networks▲6.6k3.33
[PDF]Gradient-Flow Framework for LoRA: Finite-Stepsize Guarantees and Rank-Dependent Implicit Bias▼1611.50
[PDF]The Spectral Shortcut: How a Fast Contextual Pathway Suppresses Spectral Learning in Serial Spectral–Spatial Models▼4.3k2.00
Withdrawn or desk rejected (106)
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00
[PDF]Beyond Training Loss: Full-Space Certificates for Neural JKO and Wasserstein EvolutionDesk rejected
[PDF]Certified Frozen-Midpoint Neural Integrators: Original-Energy Dissipation and Second-Order Physical TimeDesk rejected1.33
[PDF]Certified Quotient Natural Gradients in Wasserstein Space: Retractions, Ravines, and Higher-Order CollisionsDesk rejected