I am a final-year PhD student in Computer Science at ETH Zurich under the supervision of Andreas Krause and member of Learning and Adaptive Systems Group. I am also associated with the ETH AI Center. I work on sequential decision-making and representation learning for structured data, such as point clouds or graphs.
Research interests
The main question that motivates my research is: How can we actively learn new complex environments?
My interests span multiple topics around sequential decision-making, bayesian optimization, representation learning, generative modeling.
I am sparked by designing robust algorithms with quantified uncertainty and well-understood limitations (theoretically and empirically), that would be applicable in society-critical areas.
Prior to ETH, I studied Maths, Physics, and Data Science at MIPT and Skoltech – Moscow universities with great people and great courses. I worked on deep learning for weakly-supervised semantic segmentation under the supervision of Victor Lempitsky and interned at Columbia University under the co-supervision of Hod Lipson. I did ML internships at Yandex (deep learning for precipitation nowcasting) and Amazon Web Services (Bayesian optimization for AutoML).
-
MSc in Data Analysis, 2017
Skolkovo Institute of Science and Technology (Skoltech), Moscow
-
MSc in Applied Mathematics (with honors), 2017
Moscow Institute of Physics and Technology (Phystech), Moscow
-
BSc in Applied Math and Physics (with honors), 2015
Moscow Institute of Physics and Technology (Phystech), Moscow
News
- August 2023: New paper on Adversarial Causal BO is now available on arXiv.
- July 2023: New work on Safe Risk-averse Bayesian Optimization for Controller Tuning is now available on arXiv.
- May 2023: Attending ICLR in Rwanda, giving oral presentation for Model-based Causal BO, talk
- April 2023: Joining Google DeepMind, Brain team, as a reseach intern, going to dive into RL from human feedback for LLM
- January 2023: Model-based Causal BO accepted to ICLR featured spotlight (top 25% of accepted papers)
- August 2022: Invited to speak at Google TechTalk (Google BayesOpt Speaker Series), slides and video are available.
- August 2022: Invited to speak at AWS ML Science Tech Presentations series, slides are available.
- Summer 2022: Our paper got the best paper award at AutoML Conf! I was invited to give the contributed talk, recording is here. An intuitive blog post at Amazon Science is here.
- Spring 2022: Automatic Termination for Hyperparameter Optimization accepted to AutoML Conf 2022.
- Fall 2021: Risk-averse Heteroscedastic Bayesian Optimization accepted to NeurIPS 2021.
- Summer 2021: Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation accepted at ICCV 2021.
- Spring 2021: Overfitting in Bayesian Optimization: an empirical study and early-stopping solution accepted to ICLR Workshop on Neural Architecture Search. Video is here.
- Fall 2020: I am a Head TA of my favorite ETH course Probabilistic Artificial Intelligence.
- Summer 2020: Interning at Amazon Web Services, Berlin
- Spring 2020: Hierarchical Image Classification using Entailment Cone Embeddings accepted to CVPR 2020 Workshop on Differential Geometry.
Publications
Experience
Research areas: Probabilistic Machine Learning, Bayesian Optimization, Deep Learning, Tensors, Computer Vision
Advisor: Prof. Andreas Krause
Worked with Hod Lipson and collaboration with Victor Lempitsky.
- Worked on deep learning based methods for weakly-supervised semantic segmentation
- Developed an efficient architecture for image-based plant disease detection
Teaching
- Head Teaching assistant: lead course reorganization, teaching and examination
- Probabilistic Artificial Intelligence at ETH, 2020 (600 students course and 30 TAs)
- Teaching assistant: create howeworks, projects, teach tutorials, supervise exam
- Probabilistic Artificial Intelligence at ETH, 2018, 2019
- Introduction to Machine Learning at ETH, 2018, 2019
- Advanced Topics in Machine Learning at ETH, 2017, 2018
- Data Mining: Learning from Large Data Sets at ETH, 2017
- Signal and Image Processing by Prof. Stamatios Lefkimmiatis at Skoltech, 2017
Supervised theses
I (co-)supervised MSc theses of several bright students, some resulting into research publications:
- Alicja Chaszczewicz: Following Gradients to Calibrate Equilibrium Reaching Simulators,
jointly with Max Paulus, ETH Zurich, December 2020 - May 2021. - Ankit Dhall: Learning Representations for Images With Hierarchical Labels (paper @DiffCVML'20),
jointly with Octavian Ganea and Dario Pavllo, ETH Zurich, March - September 2019. - Erik Daxberger: Mixed-Variable Bayesian Optimization (paper IJCAI'20),
jointly with Matteo Turchetta, ETH Zurich, October 2018 - April 2019. - Stefan Beyeler: Multi-fidelity Batch Bayesian Optimization for the Calibration of Transport System Simulations,
jointly with Matteo Turchetta, ETH Zurich, October 2017 - April 2018.