My current research interests in algorithmic discovery via deep learning, and deep learning in data-constrained regimes. If you want to know more about my work or work with me, take a look at my papers.

Janardhan Kulkarni. Microsoft Research, Redmond. Verified email at cs.washington.edu. ... J Allen, B Ding, J Kulkarni, H Nori, O Ohrimenko, S Yekhanin. Advances in Neural Information Processing Systems 32, 2019. 46: 2019: Fast and memory efficient differentially private-sgd via jl …

The Simons Institute for the Theory of Computing is the world's leading venue for collaborative research in theoretical computer science.

Janardhan Kulkarni, Yin Tat Lee, Daogao Liu: Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps. CoRR abs/2103.15352 (2021)

2023年8月26日 · Invited talk by Janardhan (Jana) Kulkarni and Contributed Talks III, both presented at the 5th Privacy-Preserving Machine Learning Workshop (PPML) 2023, an a...

Janardhan Kulkarni (Preferred) Suggest Name; Emails ****@microsoft.com (Confirmed) Suggest Email; Personal Links. Google Scholar. DBLP. Suggest URL; Career & Education History. Microsoft Research, Redmond. Microsoft (microsoft.com)

Jayashree Mohan, Amar Phanishayee, and Janardhan Kulkarni, Microsoft Research; Vijay Chidambaram, University of Texas at Austin and VMware Research. Training Deep Neural Networks (DNNs) is a popular workload in both enterprises and cloud data centers.

2023年8月2日 · View a PDF of the paper titled Optimal Online Discrepancy Minimization, by Janardhan Kulkarni and 1 other authors

Janardhan Kulkarni's 18 research works with 259 citations and 389 reads, including: Non-clairvoyantly Scheduling to Minimize Convex Functions

Janardhan Kulkarni's 19 research works with 430 citations and 724 reads, including: Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping