Search papers, labs, and topics across Lattice.
Brandeis University, Waltham, MA, USA
3
16
5
3
SVRG, a popular variance reduction method, finally gets its generalization guarantees rigorously established, revealing optimal excess population risk bounds.
Momentum doesn't hurt generalization in SGDM, and this paper proves it with tight stability bounds applicable to both Polyak's and Nesterov's variants.
Achieving up to 3.2x speedup in recommender system inference across multiple hardware platforms without manual tuning could revolutionize deployment strategies in heterogeneous environments.
