{"total":22,"rows":[{"id":"2102.08446","title":"Smoothed Analysis with Adaptive Adversaries","created":"2021-02-16","cited_by_count":57,"area":null},{"id":"2105.05842","title":"Kernel Thinning","created":"2021-05-12","cited_by_count":47,"area":null},{"id":"2303.07160","title":"Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond","created":"2023-03-13","cited_by_count":22,"area":null},{"id":"2205.10733","title":"GraB: Finding Provably Better Data Permutations than Random Reshuffling","created":"2022-05-22","cited_by_count":19,"area":null},{"id":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16,"area":null},{"id":"2312.00073","title":"Binary perceptrons capacity via fully lifted random duality theory","created":"2023-11-29","cited_by_count":13,"area":null},{"id":"2312.16531","title":"Fl RDT based ultimate lowering of the negative spherical perceptron capacity","created":"2023-12-27","cited_by_count":11,"area":null},{"id":"2502.07861","title":"Streaming Attention Approximation via Discrepancy Theory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2302.00845","title":"Coordinating Distributed Example Orders for Provably Accelerated Training","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2502.12063","title":"Low-Rank Thinning","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2506.19276","title":"Rare dense solutions clusters in asymmetric binary perceptrons -- local entropy via fully lifted RDT","created":"2025-06-24","cited_by_count":5,"area":null},{"id":"2410.20646","title":"Injectivity capacity of ReLU gates","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2412.18184","title":"Unified Stochastic Framework for Neural Network Quantization and Pruning","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2511.01037","title":"Binary perceptron computational gap -- a parametric fl RDT view","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2601.10628","title":"Parametric RDT approach to computational gap of symmetric binary perceptron","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2209.01147","title":"Algorithms for Discrepancy, Matchings, and Approximations: Fast, Simple, and Practical","created":"2022-09-02","cited_by_count":0,"area":null},{"id":"2309.10975","title":"SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2309.16809","title":"GraB-sampler: Optimal Permutation-based SGD Data Sampler for PyTorch","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2604.19712","title":"Ultrametric OGP - parametric RDT \\emph{symmetric} binary perceptron connection","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.10944","title":"Express Language Modeling","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.06327","title":"Query-Oblivious Coresets for Softmax Attention: Improved Bounds and Efficient Constructions","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}