Dravyansh Sharma

I am currently an IDEAL Postdoc in Chicago. I completed my PhD in the Computer Science Department at the Carnegie Mellon University, and was fortunate to be advised by Nina Balcan. I am interested in designing algorithms for machine learning with strong and provable performance guarantees.

Recent news    

Research     Résumé     Reach me

   

   

   

   

   

Recent News and Highlights

  • December 2025
  • ★ Attending NeurIPS 2025 in San Diego. Come to our tutorial!
  • ★ Presenting six accepted papers at NeurIPS 2025 (three in the main conference, three in workshops). Meet me at the poster sessions!
  • • Giving a talk at the Chicago Junior Theorists Workshop 2025.
  • November 2025
  • ★ Teaching a new course TTIC 31290 - Machine Learning for Algorithm Design with Avrim Blum (Fall 2025).
  • ★ Invited to serve as an Area Chair for ICML 2026.
  • • Organizing the poster session for the IDEAL Get Ready for Research Workshop 2025.
  • • New on arXiv "Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem", joint with Avrim Blum, Marten Garicano, and Kavya Ravichandran.
  • October 2025
  • • Gave a talk "Hyperparameter Optimization and Algorithm Selection" at INFORMS 2025, Atlanta.
  • ★ Three papers accepted at NeurIPS 2025 workshops:
  •   • OPT2025, Optimization for Machine Learning.
  •   • Reliable ML from Unreliable Data.
  •   • DiffCoALG: Differentiable Learning of Combinatorial Algorithms.
  • September 2025
  • ★ Three papers accepted at NeurIPS 2025 (including a spotlight)! Congratulations to all my co-authors (Nina Balcan, Avrim Blum, Zhiyuan Li, Anh Nguyen and Alec Sun)!
  • • Gave a talk at the Theory Seminar at the Johns Hopkins University.
  • • Gave a tutorial at AutoML 2025, "Limitations of State-of-the-Art and a New Principled Framework for HPO and Algorithm Selection".
  • • Gave a talk "Configuring neural networks and tuning gradient descent hyperparameters" at the Algorithms Seminar at Northwestern University.
  • August 2025
  • ★ Attending IJCAI 2025 in Montreal. Poster of our work invited to the Best Paper from Sister Conferences Track.
  • • Gave a talk titled "Towards Principled Hyperparameter Optimization and Algorithm Selection" at Université de Montréal.
  • • Presented a poster at the wonderful Incentives for Collaborative Learning and Data Sharing Summer Workshop at TTIC.
  • ★ Our proposal (joint with Nina Balcan and Colin White) has been accepted as one of the NeurIPS 2025 tutorials!
  • July 2025
  • ★ Awarded Top Reviewer at UAI 2025.
  • • Our work Algorithm Configuration for Structured Pfaffian Settings (joint with Nina Balcan and Anh Nguyen) accepted for presentation at AutoML 2025 non-archival track.
  • ★ Attending UAI 2025 in Rio de Janeiro. Come to my in-person tutorial!
  • ★ Attending ICML 2025 in Vancouver. Video of our work.
  • • New on arxiv Distribution-dependent Generalization Bounds for Tuning Linear Regression Across Tasks (with Nina Balcan and Saumya Goyal).
  • June 2025
  • ★ My proposal "Limitations of State-of-the-Art and a New Principled Framework for HPO and Algorithm Selection" has been accepted as one of the 2025 AutoML tutorials.
  • • Gave a talk "Principled Hyperparameter Optimization and Algorithm Selection" at the Capital Area Theory Seminar (CATS) at the University of Maryland, College Park.
  • • Helped organize IDEAL Annual Meeting (with Lev Reyzin). Gave a talk titled "Principled Hyperparameter Tuning and Algorithm Selection" at the University of Illinois Chicago.
  • • Five accepted workshop papers (three at ICML 2025, one at IJCAI 2025, one at UAI 2025).
  • • New on arxiv Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning (with Alec Sun).
  • May 2025
  • ★ Our work On Learning Verifiers for Chain-of-Thought Reasoning (joint with Nina Balcan, Avrim Blum and Zhiyuan Li) is available as a pre-print.
  • ★ New on arxiv Learning accurate and interpretable tree-based models (joint with Nina Balcan), an extended version of earlier work that won the Outstanding Student Paper Award at UAI 2024.
  • • Presented a poster at the "Midwest Optimization & Statistical Learning Conference 2025" at Northwestern University.
  • • Our work Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees (joint with Ally Du and Eric Huang) accepted at UAI 2025.
  • • Our work (joint with Nina Balcan) Learning Accurate and Interpretable Decision Trees (Extended Abstract) accepted at the Best Paper Track for Sister Conferences at IJCAI 2025.
  • • Our work PAC Learning with Improvements (joint with Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless and Matthew Walter) accepted at ICML 2025.
  • • Our paper titled Algorithm Configuration for Structured Pfaffian Settings (joint with Nina Balcan and Anh Nguyen) published in TMLR 2025.
  • April 2025
  • • Gave a talk at TTIC on our recent work Provable tuning of deep learning model hyperparameters (joint with Nina Balcan and Anh Nguyen).
  • ★ My proposal Hyperparameter Optimization and Algorithm Selection: Practical Techniques, Theory, and New Frontiers has been accepted as one of the 2025 UAI tutorials. Stay tuned!
  • ★ Invited to serve as an Area Chair at NeurIPS 2025.
  • • Presented our work Provable tuning of deep learning model hyperparameters (joint with Nina Balcan and Anh Nguyen) at the IDEAL workshop on "Understanding the Mechanisms of Deep Learning and Generative Modeling" at Northwestern University.
  • • Gave a talk titled Provable tuning of deep learning model hyperparameters (based on joint work with Nina Balcan and Anh Nguyen) at the Theory lunch at the University of Chicago.
  • March 2025
  • ★ Session Chair at AAAI 2025 sessions on Constraint Satisfaction and Optimization.
  • • Our work titled PAC Learning with Improvements (joint with Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless and Matthew Walter) available as a pre-print.
  • • Attending AAAI 2025 in Philly. Presenting Offline-to-online hyperparameter transfer for stochastic bandits, joint work with Arun Suggala.

Publications

Home

            Contact:    

E-mail: dravy [AT] ttic [DOT] edu
Office: 434, Toyota Technological Institute at Chicago, 6045 S Kenwood Ave, Chicago, IL 60637