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
53 results for “keyword:"precondition"” in ICLR 2027. 6 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ScaledGD for Underparameterized Matrix Factorization: Global Convergence and Stepsize Universality▲603.50
[PDF]The Rank Bottleneck in Diffusion Transformers: Why and When Width Must Track Token Dimension▲502.75
[PDF]The Noise-Transmission Burden of Diffusion Network: Why Image Prediction Can Outperform Noise Prediction▼5.8k2.33
[PDF]ChromaMuon: Spectral Optimizer Diagnostics and Design with Retained Newton–Schulz Coordinates▼1.2k1.67
[PDF]Learning EEG Structure in Its Native Coordinates: Operator-Preconditioned Multi-View Pretraining▲5.4k3.00
[PDF]Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach▲5.4k3.00
[PDF]How Does Orthogonalization Adapt to the Neural Network Hessian Structure? A Gradient Self Outer-Product Analysis at Initialization▲3.0k2.33
[PDF]Non-Convex Online SGD with Dependent Data: Last-Iterate Convergence and Temporal Preconditioning▼1.2k1.67
[PDF]Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression▲1.7k3.33
[PDF]Breaking the Black Box: An Architecture-Specialized Preconditioning Optimizer for Attention Mechanism▼4.3k2.00
[PDF]Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss▼5.8k2.33
Withdrawn or desk rejected (6)
[PDF]Learning Iteration Schedules, Not Inverses: Zero-Shot Amortized Neural Preconditioning for Large-Scale Linear SystemsDesk rejected
[PDF]Same Function, Different Geometry: Choosing Optimization Coordinates for Gaussian RepresentationsWithdrawn1.50
[PDF]Growing in the Right Coordinates: Schur-Gated Function-Preserving Network ExpansionWithdrawn1.33