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
229 results for “keyword:"approximation"” in ICLR 2027. 27 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When a Nearby Center Is Not Enough: Service-Aware Individual Fairness for Min-Sum-Radii Clustering▼5.8k2.33
[PDF]Approximation Algorithms for Dual-Memory Request Scheduling in Disaggregated LLM Inference▼4.3k2.00
[PDF]Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning▼4.3k2.00
[PDF]Direct Message Approximation (DMA): A Consistency-Based Framework for Tractable Approximate Inference on Factor Graphs▼5.9k2.50
[PDF]Markovian Nonconvex ADMM for Reinforcement Learning: Bellman-Resolvent Stability Beyond Smooth Blocks▲3.0k2.33
[PDF]Efficiency of Diffusion Models for Infinite-dimensional Data Generation: Dimension Independent Approximation and Estimation Errors▲4002.67
[PDF]Decoupled Polynomial State-Space Iterations for Matrix Polar Approximation, with an Application to Muon▼4.3k2.00
[PDF]Policy Improvement and Preservation in Continual Reinforcement Learning with Latent Families▼4.3k2.00
[PDF]Online Geometric Optimization via Projection, Hierarchical Discretization, and Convex Relaxation▼4.5k2.25
[PDF]Scalable Quantum Machine Learning via Multi-layer Fully-Connected Variational Quantum Circuits▲6.1k2.00
[PDF]Universal 2.030-Rounding for Multilayer Correlation Clustering with Probability Weights▲6.1k2.00
[PDF]Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization▼1.2k1.67
[PDF]Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation▲11.00
[PDF]How Much Rank Does LoRA Need? Task-Dependent Rank-Error Bounds for Transformer Attention▼1.2k1.67
[PDF]FReS: Factorized Recurrent State for Efficient Inference with Gated Delta-Rule Linear Attention▼4.5k2.67
[PDF]Is Dense Supervision Worth Its Cost? A Budget-Controlled Study of Supervision Allocation in MAML▼4.3k2.00
Withdrawn or desk rejected (27)
[PDF]Low-Rank Recovery of High-Order Neighbor Structure for Scalable Multi-View ClusteringWithdrawn2.00
[PDF]Certified Best-First Sparse Attention: Provable Early Termination via Admissible Block BoundsWithdrawn2.00