{"total":21,"rows":[{"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":"2210.08371","title":"Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability","created":"2022-10-15","cited_by_count":25,"area":null},{"id":"2210.03961","title":"Dynamic Tensor Product Regression","created":"2022-10-08","cited_by_count":17,"area":null},{"id":"2307.06565","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","created":"2023-07-13","cited_by_count":11,"area":null},{"id":"2104.00816","title":"Partition-Guided GANs","created":"2021-04-02","cited_by_count":9,"area":null},{"id":"2106.08601","title":"Self-Supervised GANs with Label Augmentation","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2305.17482","title":"Federated Empirical Risk Minimization via Second-Order Method","created":"2023-05-27","cited_by_count":9,"area":null},{"id":"2309.07452","title":"Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2201.11205","title":"Generative Trees: Adversarial and Copycat","created":"2022-01-26","cited_by_count":7,"area":null},{"id":"2211.14694","title":"DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data","created":"2022-11-27","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":"2307.16422","title":"Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution","created":"2023-07-31","cited_by_count":3,"area":null},{"id":"2508.19857","title":"Quantum latent distributions in deep generative models","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2112.02446","title":"Fast Graph Neural Tangent Kernel via Kronecker Sketching","created":"2021-12-04","cited_by_count":2,"area":null},{"id":"2112.09842","title":"Manifold embedding data-driven mechanics","created":"2021-12-18","cited_by_count":2,"area":null},{"id":"2410.22381","title":"Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2509.11178","title":"StegOT: Trade-offs in Steganography via Optimal Transport","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2108.02353","title":"Alleviating Mode Collapse in GAN via Diversity Penalty Module","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2309.01030","title":"Online Adaptive Mahalanobis Distance Estimation","created":"2023-09-02","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":"2403.07463","title":"Backdoor Attack with Mode Mixture Latent Modification","created":"2024-03-12","cited_by_count":0,"area":null}],"next_cursor":null}