Tag
微软研究院及其合作者通过人类主导的智能体研究流程，解决了存在31年之久的KLS猜想，确立了对数凹分布的普适几何原理，并经独立研究者验证与机器形式化检验确认，为高维采样与随机算法效率理解扫清重大理论障碍。
This paper improves the optimal expected mistake bound for randomized proper online learning, showing it is O(L(H) log T), which is optimal up to a universal constant for worst-case classes.
This paper introduces a novel semi-tensor product for tensors and develops a multi-term randomized tensor singular value decomposition (MSTP-SVD) to improve low-rank approximation accuracy and computational efficiency for visual data processing tasks.
This paper presents a randomized algorithm that solves k-coloring on n-vertex graphs in time (2-ε_k)^n for every fixed k, resolving a long-standing open problem in exponential-time algorithms. It builds on hypergraph containers and list-coloring reductions.
RGLD combines global random-feature density estimation with local neighbor analysis for efficient unsupervised tabular anomaly detection, achieving top AUROC performance on 47 datasets while being 50x-580x faster than deep detectors.
This paper introduces a new differential privacy sketching mechanism based on fast transforms that achieves state-of-the-art privacy guarantees and improved runtime, and applies it to DP linear regression to obtain the first fast method for DP ordinary least squares.