Recent Papers

• DDPM Score Matching and Distribution Learning COLT 2026
  with Sinho Chewi, Anay Mehrotra and Omar Montasser
  Short Best Paper Award @ ICLR 2025 Workshop on Deep Generative Models in Machine Learning
• Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases and Beyond COLT 2026
  with Anay Mehrotra and Felix Zhou
• Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms STOC 2026
  with Pravesh Kothari, Shuchen Li and Manolis Zampetakis
• On the Learning Curves of Revenue Maximization STOC 2026
  with Steve Hanneke, Shay Moran and Grigoris Velegkas
• Mean Estimation from Coarse Data: Characterizations and Efficient Algorithms ICLR 2026
  with Anay Mehrotra, Manolis Zampetakis, Felix Zhou and Ziyu Zhu
• On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability ALT 2026
  with Anay Mehrotra and Grigoris Velegkas
• What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness

  COLT 2025
  with Yang Cai, Katerina Mamali, Anay Mehrotra and Manolis Zampetakis

  Best Paper Award
• Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion ICML 2025
  with Kulin Shah, Adam Klivans and Giannis Daras
• On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse STOC 2025
  with Anay Mehrotra and Grigoris Velegkas

Pre-prints

• Transfer Learning Beyond Bounded Density Ratios
  with Ilias Zadik and Manolis Zampetakis

Teaching

Service