Mojmír Mutný

Mojmír Mutný

Researcher

ETH Zurich

I am a researcher at ETH Zurich working in the research group of Andreas Krause, Learning and Adaptive Systems group. My current research work mostly focuses on modern instances of Experimental Design – addressing the search for the most informative experiments in order to infer an unknown statistical quantity.

I am also interested in/have worked on Bayesian optimization, kernel methods, sensor selection, control, bandit algorithms and convex optimization. Some of my algorithms have found application in machine calibration, spatial analysis and protein design.

Interests

  • Mathematical Optimization
  • Machine Learning
  • Active Learning
  • Experimental design
  • Bandit Algorithms
  • Protein Design

Education

  • PhD in Computer Science, 2018-2024

    ETH Zurich

  • MSc in Computational Science, 2017

    ETH Zurich

  • BSc in Mathematical Physics, 2015

    University of Edinburgh

Recent Posts

Publications

Sequential Experimental Design and Optimization with Structural Assumptions: Additivity and Subspaces

Mojmı́r Mutný, Andreas Krause

Transition Constrained Bayesian Optimization via Markov Decision Processes

arXiv

Active Exploration via Experiment Design in Markov Chains

A key challenge in science and engineering is to design experiments to learn about some unknown quantity of interest. Classical …
Mojmı́r Mutný, Tadeusz Janik, Andreas Krause
DOI URL

Enhanced Sequence-Activity Mapping and Evolution of Artificial Metalloenzymes by Active Learning

PDF

Likelihood Ratio Confidence Sets for Sequential Decision Making

Nicolas Emmenegger*, Mojmı́r Mutný*, Andreas Krause
URL

Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design

PDF

Submodular Reinforcement Learning

URL

Experimental Design of Linear Functionals in Reproducing Kernel Hilbert Spaces

Optimal experimental design seeks to determine the most informative allocation of experiments to infer an unknown statistical …
Mojmı́r Mutný, Andreas Krause
URL

Tuning particle accelerators with safety constraints using Bayesian optimization

DOI URL

Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes

In this work we introduced DPP-BBO, a natural and easily applicable framework for enhancing batch diversity in BBO algorithms which …
Elvis Nava, Mojmı́r Mutný, Andreas Krause
PDF

Sensing Cox Processes via Posterior Sampling and Positive Bases

We study adaptive sensing of Cox point processes, a widely used model from spatial statistics. We introduce three tasks: maximization …
Mojmı́r Mutný, Andreas Krause
URL

No-regret Algorithms for Capturing Events in Poisson Point Processes

Inhomogeneous Poisson point processes are widely used models of event occurrences. We address emphadaptive sensing of Poisson Point …
Mojmı́r Mutný, Andreas Krause
PDF

Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback

Combinatorial bandits with semi-bandit feedback generalize multi-armed bandits, where the agent chooses sets of arms and observes a …
URL

Learning Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

We present the first approach for learning–from a single trajectory–a linear quadratic regulator (LQR), even for unstable …
URL

Data Summarization via Bilevel Optimization

The increasing availability of massive data sets poses a series of challenges for machine learning. Prominent among these is the need …
arXiv

MakeSense: Automated Sensor Design for Proprioceptive Soft Robots

Soft robots have applications in safe human–robot interactions, manipulation of fragile objects, and locomotion in challenging …
URL

Convergence Analysis of Block Coordinate Algorithms with Determinantal Sampling

We analyze the convergence rate of the randomized Newton-like method introduced by Qu et. al. (2016) for smooth and convex objectives, …
Mojmı́r Mutný, Michal Derezisnki, Andreas Krause
PDF

Coresets via Bilevel Optimization for Continual Learning and Streaming

Coresets are small data summaries that are sufficient for model training. They can be maintained online, enabling efficient handling of …
Zalán Borsos, Mojmı́r Mutný, Andreas Krause
URL

Experimental Design for Optimization of Orthogonal Projection Pursuit Models

Bayesian optimization and kernelized bandit algorithms are widely used techniques for sequential black box function optimization with …
Mojmı́r Mutný, Johannes Kirschner, Andreas Krause
PDF

Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces

Bayesian optimization is known to be difficult to scale to high dimensions, because the acquisition step requires solving a non-convex …
arXiv

Bayesian Optimization for Fast and Safe Parameter Tuning of SwissFEL

Parameter tuning is a notoriously time-consuming task in accelerator facilities. As tool for global optimization with noisy …
PDF

Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features

We develop an efficient and provably no-regret Bayesian optimization (BO) algorithm for optimization of black-box functions in high …
PDF

Parallel Stochastic Newton Method

We propose a parallel stochastic Newton method (PSN) for minimizing unconstrained smooth convex functions. We analyze the method in the …
Mojmı́r Mutný, Peter Richtárik
PDF

Code

Sensing Poisson Point Processes for Python (sensepy)

It provides an efficient finite basis approximation for RBF and Matern kernels in low dimensions.
Dec 31, 2023

Quadrature Fourier Features (QFF) for Python

This repository includes the code used in paper:Mojmir Mutny & Andreas Krause, “Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features”, NIPS 2018 It provides an efficient finite basis approximation for RBF and Matern kernels in low dimensions.
Dec 31, 2018