Skip to content
conftrace_

Janardhan Kulkarni

26 papers · 2016–2026 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+9 more ↓ πŸ—ΊοΈ Taxonomy Completionist (42) πŸƒ Academic Marathon Β· Half 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
πŸ”¬ Deep Specialist (16) 🧬 Topic Evolution πŸ’Ž Century Club Β· Bronze ⚑ Prolific Year Β· Productive πŸ“ˆ Trend Setter πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner πŸ—ƒοΈ Keyword Collector (124) 🌈 Renaissance Researcher (6)

Venues

NeurIPS (8) ICLR (6) ICML (4) OSDI (4) COLT (2) AISTATS (1) EMNLP (1)

Top co-authors

Sivakanth Gopi (8) Sergey Yekhanin (6) Yin Tat Lee (5) Arturs Backurs (5) Harsha Nori (3) Huseyin A Inan (3) Gautam Kamath (3) Sriram Rao (2) Huseyin A. Inan (2) Huanyu Zhang (2)

Research topics

Machine Learning (20) Application Areas (17) Deep Learning (9) Security & Privacy (9) Differential Privacy (8) Optimization & Theory Β· Machine Learning (7) Artificial Intelligence (6) Mathematics & Optimization (6) Core AI (6) Computer Science (4) Natural Language Processing (4) Core Methods (4) Optimization (4) Optimization & Theory Β· Deep Learning (4) Systems (4)

Keywords

differential privacy (17) large language model (4) resource allocation (3) local differential privacy (3) lower bound (2) synthetic data generation (2) online algorithm (2) privacy-utility trade-off (2) language model (2) local privacy (2) foundation model (2) private fine-tuning (2) information extraction (1) in-context learning (1) privacy attack (1) structure learning (1) transfer learning (1) representation learning (1) quantization (1) image generation (1)

Papers

VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination OSDI 2026 DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory COLT 2025 Towards Foundation Models for Mixed Integer Linear Programming ICLR 2025 Differentially Private Synthetic Data via Foundation Model APIs 1: Images ICLR 2024 Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation ICLR 2024 Privately Aligning Language Models with Reinforcement Learning ICLR 2024 Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks EMNLP 2023 Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping ICLR 2023 Differentially Private Fine-tuning of Language Models ICLR 2022 Differentially Private Model Compression NeurIPS 2022 Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters OSDI 2022 When Does Differentially Private Learning Not Suffer in High Dimensions? NeurIPS 2022 Accuracy, Interpretability, and Differential Privacy via Explainable Boosting ICML 2021 Consistent k-Median: Simpler, Better and Robust AISTATS 2021 Differentially Private Correlation Clustering ICML 2021 Differentially Private n-gram Extraction NeurIPS 2021 Fast and Memory Efficient Differentially Private-SGD via JL Projections NeurIPS 2021 Private Non-smooth ERM and SCO in Subquadratic Steps NeurIPS 2021 Differentially Private Set Union ICML 2020 Locally Private Hypothesis Selection COLT 2020 Privately Learning Markov Random Fields ICML 2020 An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors NeurIPS 2019 Locally Private Gaussian Estimation NeurIPS 2019 Collecting Telemetry Data Privately NeurIPS 2017 GRAPHENE: Packing and Dependency-Aware Scheduling for Data-Parallel Clusters OSDI 2016 Morpheus: Towards Automated SLOs for Enterprise Clusters OSDI 2016