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
- May 2025. 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.
- May 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.
- May 2025. Our work PAC Learning with Improvements (joint with Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless and Matthew Walter) accepted at ICML 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).
- April 2025. 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!
- April 2025. Invited to serve as an Area Chair at NeurIPS 2025.
- April 2025. Our paper titled Algorithm Configuration for Structured Pfaffian Settings (joint with Nina Balcan and Anh Nguyen) has been accepted for publication at TMLR.
- April 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.
- April 2025. 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.
- March 2025. 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.
- Feb-March 2025. Attending AAAI 2025 in Philly. Presenting Offline-to-online hyperparameter transfer for stochastic bandits, joint work with Arun Suggala.
- Feb 2025. Our work titled Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees (joint with Ally Du and Eric Huang) is available as a pre-print.
- Jan 2025. Our work titled Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function (joint with Nina Balcan and Anh Nguyen) is available as a pre-print.
- Dec 2024. Attended NeurIPS 2024 in Vancouver to present two posters.
- Sep 2024. Started as a postdoc at IDEAL (The Institute for Data, Econometrics, Algorithms, and Learning), part of NSF TRIPODS, hosted by Avrim Blum (TTIC) and Aravindan Vijayaraghavan (Northwestern).
- July 2024. Our work (joint with Nina Balcan) Learning Accurate and Interpretable Decision Trees won the Outstanding Student Paper Award at UAI 2024.
Publications
- Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees, UAI 2025 with Ally Yalei Du and Eric Huang
- Learning Accurate and Interpretable Decision Trees (Extended Abstract), IJCAI 2025 (Best Papers from Sister Conferences Track) with Maria-Florina Balcan
- PAC Learning with Improvements, ICML 2025 with Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless and Matthew Walter
- Algorithm Configuration for Structured Pfaffian Settings, TMLR 2025 with Maria-Florina Balcan and Anh Tuan Nguyen
- Offline-to-online hyperparameter transfer for stochastic bandits, AAAI 2025 with Arun Sai Suggala
- An Analysis of Robustness of Non-Lipschitz Networks, NeurIPS 2024 (Journal-to-conference track) with Maria-Florina Balcan, Avrim Blum and Hongyang Zhang
- Accelerating ERM for data-driven algorithm design using output-sensitive techniques, NeurIPS 2024 with Maria-Florina Balcan and Christopher Seiler
- Learning Accurate and Interpretable Decision Trees, UAI 2024 (Outstanding student paper award) with Maria-Florina Balcan
- No Internal Regret with Non-convex Loss Functions, AAAI 2024
- Accelerating data-driven algorithm design using output-sensitive techniques, AAAI 2024 Workshop on Learnable Optimization with Maria-Florina Balcan and Christopher Seiler
- Shifting regret for tuning combinatorial algorithms with applications to clustering, AAAI 2024 Workshop on Learnable Optimization with Maria-Florina Balcan and Travis Dick
- New Bounds for Hyperparameter Tuning of Regression Problems Across Instances, NeurIPS 2023 with Maria-Florina Balcan and Anh Tuan Nguyen
- Reliable Learning for Test-time Attacks and Distribution Shift, NeurIPS 2023 with Maria-Florina Balcan, Steve Hanneke and Rattana Pukdee
- Efficiently Learning the Graph for Semi-supervised Learning, UAI 2023 with Maxwell Jones
- 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
- Provably tuning the ElasticNet across instances, NeurIPS 2022 [blog post] with Maria-Florina Balcan, Mikhail Khodak and Ameet Talwalkar
- Robustly-reliable learners under poisoning attacks, COLT 2022 with Maria-Florina Balcan, Avrim Blum and Steve Hanneke
- 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
- Data driven semi-supervised learning, NeurIPS 2021 (Oral, <1%) with Maria-Florina Balcan
- Learning-to-learn non-convex piecewise-Lipschitz functions, NeurIPS 2021 with Maria-Florina Balcan, Mikhail Khodak, Ameet Talwalkar
- Learning Piecewise Lipschitz Functions in Changing Environments, AISTATS 2020 [slides] with Maria-Florina Balcan and Travis Dick
- Better morphology prediction for better speech systems, Interspeech 2019 with Melissa Wilson and Antoine Bruguier
- On Training and Evaluation of Grapheme-to-Phoneme Mappings with Limited Data, Interspeech 2018
- Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme Prediction, Interspeech 2018 with Antoine Bruguier and Anton Bakhtin
- 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
- On greedy maximization of entropy, ICML 2015 with Amit Deshpande and Ashish Kapoor
-