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 and Highlights
- 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
- 2025
- [C20] PAC Learning with Improvements, ICML 2025 with Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless and Matthew Walter
- [C19] Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees, UAI 2025 with Ally Yalei Du and Eric Huang
- [C18] Offline-to-online hyperparameter transfer for stochastic bandits, AAAI 2025 with Arun Sai Suggala
- [J3] Algorithm Configuration for Structured Pfaffian Settings, TMLR 2025 with Maria-Florina Balcan and Anh Tuan Nguyen
- [A1] Learning Accurate and Interpretable Decision Trees (Extended Abstract), IJCAI 2025 (Best Papers from Sister Conferences Track) with Maria-Florina Balcan
- [W9] PAC Learning with Improvements, 2nd Workshop on Social Choice and Learning Algorithms (IJCAI 2025) with Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless and Matthew Walter
- [W8] Learning how to step in gradient-based optimization: beyond convexity and smoothness, 3rd Workshop on High-dimensional Learning Dynamics (ICML 2025)
- [W7] Gradient descent in presence of extreme flatness and steepness, Methods and Opportunities at Small Scale (ICML 2025)
- 2024
- [T1] CMU CSD PhD Thesis Data-driven algorithm design and principled hyperparameter tuning in machine learning
- [C17] An Analysis of Robustness of Non-Lipschitz Networks, NeurIPS 2024 (Journal-to-conference track) with Maria-Florina Balcan, Avrim Blum and Hongyang Zhang
- [C16] Accelerating ERM for data-driven algorithm design using output-sensitive techniques, NeurIPS 2024 with Maria-Florina Balcan and Christopher Seiler
- [C15] Subsidy for repair in component maintenance games, EMI/PMC 2024 with Maria-Florina Balcan and Matteo Pozzi
- [C14] Learning Accurate and Interpretable Decision Trees, UAI 2024 (Outstanding student paper award) with Maria-Florina Balcan
- [C13] No Internal Regret with Non-convex Loss Functions, AAAI 2024
- [W6] Theoretical Analyses of Hyperparameter Selection in Graph-Based Semi-Supervised Learning, ICML 2024Workshop on Geometry-grounded Representation Learning and Generative Modeling with Ally Yalei Du and Eric Huang
- [W5] Accelerating data-driven algorithm design using output-sensitive techniques, AAAI 2024 Workshop on Learnable Optimization with Maria-Florina Balcan and Christopher Seiler
- [W4] Shifting regret for tuning combinatorial algorithms with applications to clustering, AAAI 2024 Workshop on Learnable Optimization with Maria-Florina Balcan and Travis Dick
- 2023
- [C12] New Bounds for Hyperparameter Tuning of Regression Problems Across Instances, NeurIPS 2023 with Maria-Florina Balcan and Anh Tuan Nguyen
- [C11] Reliable Learning for Test-time Attacks and Distribution Shift, NeurIPS 2023 with Maria-Florina Balcan, Steve Hanneke and Rattana Pukdee
- [C10] Efficiently Learning the Graph for Semi-supervised Learning, UAI 2023 with Maxwell Jones
- [J2] An analysis of robustness of non-Lipschitz networks, JMLR 2023 (earlier version in ICLR 2022 SRML workshop) with Maria-Florina Balcan, Avrim Blum and Hongyang Zhang
- 2022
- [C9] Provably tuning the ElasticNet across instances, NeurIPS 2022 [blog post] with Maria-Florina Balcan, Mikhail Khodak and Ameet Talwalkar
- [C8] Robustly-reliable learners under poisoning attacks, COLT 2022 with Maria-Florina Balcan, Avrim Blum and Steve Hanneke
- [W3] On the Power of Abstention and Data-Driven Decision Making for Adversarial Robustness, ICLR 2022 Workshop on Socially Responsible Machine Learning (Oral) with Maria-Florina Balcan, Avrim Blum and Hongyang Zhang
- 2021
- [C7] Data driven semi-supervised learning, NeurIPS 2021 (Oral, <1%) with Maria-Florina Balcan
- [C6] Learning-to-learn non-convex piecewise-Lipschitz functions, NeurIPS 2021 with Maria-Florina Balcan, Mikhail Khodak, Ameet Talwalkar
- [W2] Improved pronunciation prediction accuracy using morphology, ACL SIG on Computational Morphology and Phonology (ACL 2021) with Saumya Sahai, Neha Chaudhari, Antoine Bruguier.
- [W1] Predicting and Explaining French Grammatical Gender, ACL Special Interest Group (SIG) on Typology (NAACL 2021) with Saumya Sahai
- 2020 and before
- [C5] Learning Piecewise Lipschitz Functions in Changing Environments, AISTATS 2020 [slides] with Maria-Florina Balcan and Travis Dick
- [C4] Better morphology prediction for better speech systems, Interspeech 2019 with Melissa Wilson and Antoine Bruguier
- [C3] On Training and Evaluation of Grapheme-to-Phoneme Mappings with Limited Data, Interspeech 2018
- [C2] Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme Prediction, Interspeech 2018 with Antoine Bruguier and Anton Bakhtin
- [J1] Some results on a class of mixed van der Waerden numbers, Rocky Mountain J. Math. 2018 with Kaushik Maran, Sai Praneeth Reddy and Amitabha Tripathi
- [C1] On greedy maximization of entropy, ICML 2015 with Amit Deshpande and Ashish Kapoor
-