{"total":56,"rows":[{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62,"area":null},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"area":null},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2102.10255","title":"Link Prediction with Persistent Homology: An Interactive View","created":"2021-02-20","cited_by_count":37,"area":null},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37,"area":null},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35,"area":null},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2211.12542","title":"CASSPR: Cross Attention Single Scan Place Recognition","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2210.03961","title":"Dynamic Tensor Product Regression","created":"2022-10-08","cited_by_count":17,"area":null},{"id":"2402.08616","title":"Adjustment Identification Distance: A gadjid for Causal Structure Learning","created":"2024-02-13","cited_by_count":16,"area":null},{"id":"2304.04970","title":"GRIL: A $2$-parameter Persistence Based Vectorization for Machine Learning","created":"2023-04-11","cited_by_count":13,"area":null},{"id":"2202.00916","title":"Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health","created":"2022-02-02","cited_by_count":12,"area":null},{"id":"2312.08893","title":"Solving Dense Linear Systems Faster Than via Preconditioning","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2305.08367","title":"Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2104.03936","title":"BR-NS: an Archive-less Approach to Novelty Search","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2311.14823","title":"Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters","created":"2023-11-24","cited_by_count":7,"area":null},{"id":"2408.06395","title":"Fast John Ellipsoid Computation with Differential Privacy Optimization","created":"2024-08-12","cited_by_count":7,"area":null},{"id":"2205.05937","title":"Ensemble Clustering via Co-association Matrix Self-enhancement","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2209.04876","title":"Subquadratic Kronecker Regression with Applications to Tensor Decomposition","created":"2022-09-11","cited_by_count":6,"area":null},{"id":"2304.14197","title":"Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games","created":"2023-04-27","cited_by_count":6,"area":null},{"id":"2308.08358","title":"Convergence of Two-Layer Regression with Nonlinear Units","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2107.10654","title":"Fast Low-Rank Tensor Decomposition by Ridge Leverage Score Sampling","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2107.08090","title":"Near-Optimal Algorithms for Linear Algebra in the Current Matrix Multiplication Time","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2110.15188","title":"The magnitude vector of images","created":"2021-10-28","cited_by_count":4,"area":null},{"id":"2206.01730","title":"On the complexity of nonsmooth automatic differentiation","created":"2022-06-01","cited_by_count":4,"area":null},{"id":"2207.11685","title":"Kernel Relative-prototype Spectral Filtering for Few-shot Learning","created":"2022-07-24","cited_by_count":4,"area":null},{"id":"2308.15283","title":"Structural Node Embeddings with Homomorphism Counts","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2201.00228","title":"The Complexity of Dynamic Least-Squares Regression","created":"2022-01-01","cited_by_count":3,"area":null},{"id":"2207.13008","title":"Efficient Algorithms for Sparse Moment Problems without Separation","created":"2022-07-26","cited_by_count":3,"area":null},{"id":"2308.00190","title":"Universal Majorization-Minimization Algorithms","created":"2023-07-31","cited_by_count":3,"area":null},{"id":"2109.10680","title":"rSVDdpd: A Robust Scalable Video Surveillance Background Modelling Algorithm","created":"2021-09-22","cited_by_count":2,"area":null},{"id":"2208.13778","title":"Rosenblatt's first theorem and frugality of deep learning","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2608.16884","title":"Improving the matrix multiplication exponent with modern optimization and AlphaEvolve","created":"2026-08-17","cited_by_count":2,"area":null},{"id":"2102.10732","title":"Dither computing: a hybrid deterministic-stochastic computing framework","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2107.14323","title":"Reconstruction of Random Geometric Graphs: Breaking the Omega(r) distortion barrier","created":"2021-07-29","cited_by_count":1,"area":null},{"id":"2111.06222","title":"ARISE: ApeRIodic SEmi-parametric Process for Efficient Markets without Periodogram and Gaussianity Assumptions","created":"2021-11-08","cited_by_count":1,"area":null},{"id":"2211.12880","title":"Faster Stochastic First-Order Method for Maximum-Likelihood Quantum State Tomography","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2307.10644","title":"Fisher-Rao distance and pullback SPD cone distances between multivariate normal distributions","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2103.03959","title":"Fine-Grained Complexity and Algorithms for the Schulze Voting Method","created":"2021-03-05","cited_by_count":0,"area":null},{"id":"2103.11774","title":"Clustered Hierarchical Anomaly and Outlier Detection Algorithms","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2203.13655","title":"Gransformer: Transformer-based Graph Generation","created":"2022-03-25","cited_by_count":0,"area":null},{"id":"2206.04180","title":"Learning in Distributed Contextual Linear Bandits Without Sharing the Context","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2210.06728","title":"On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2211.14708","title":"Identifying Chemicals Through Dimensionality Reduction","created":"2022-11-27","cited_by_count":0,"area":null},{"id":"2305.16878","title":"Can You Solve Closest String Faster than Exhaustive Search?","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2307.06463","title":"Efficiently-Verifiable Strong Uniquely Solvable Puzzles and Matrix Multiplication","created":"2023-07-12","cited_by_count":0,"area":null},{"id":"2308.04185","title":"Iterative Sketching for Secure Coded Regression","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2311.11429","title":"Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training","created":"2023-11-19","cited_by_count":0,"area":null},{"id":"2312.07043","title":"The Complexity of Envy-Free Graph Cutting","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2408.03085","title":"Universal Matrix Multiplication on Quantum Computer","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2410.21987","title":"Node Regression on Latent Position Random Graphs via Local Averaging","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2602.05541","title":"Reducing the Complexity of Matrix Multiplication by Quantum Computing","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.21797","title":"Neural Learning of Fast Matrix Multiplication Algorithms: A StrassenNet Approach","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2606.20082","title":"Beyond Averaging in John Ellipsoid Approximation: High-Accuracy Algorithms in the Leverage-Score Model","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}