M
Matej Balog
Researcher at Max Planck Society
Publications - 12
Citations - 753
Matej Balog is an academic researcher from Max Planck Society. The author has contributed to research in topics: Kernel (statistics) & Mondrian. The author has an hindex of 7, co-authored 11 publications receiving 506 citations. Previous affiliations of Matej Balog include University of Cambridge.
Papers
More filters
Proceedings Article
DeepCoder: Learning to Write Programs
TL;DR: In this paper, the authors train a neural network to predict properties of the program that generated the outputs from the inputs, and use the network's predictions to augment search techniques from the programming languages community, including enumerative search and an SMT-based solver.
Posted Content
DeepCoder: Learning to Write Programs
TL;DR: The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs to augment search techniques from the programming languages community, including enumerative search and an SMT-based solver.
Journal ArticleDOI
Discovering faster matrix multiplication algorithms with reinforcement learning
Alhussein Fawzi,Matej Balog,Aja Huang,Thomas Hubert,Bernardino Romera-Paredes,Mohammadamin Barekatain,Alexander Novikov,Francisco J. R. Ruiz,Julian Schrittwieser,Grzegorz Swirszcz,David Silver,Demis Hassabis,Pushmeet Kohli +12 more
TL;DR: In this paper , a deep reinforcement learning approach based on AlphaZero is used to discover efficient and provably correct algorithms for the multiplication of arbitrary matrices, where the objective is finding tensor decompositions within a finite factor space.
Proceedings Article
Differentially Private Database Release via Kernel Mean Embeddings
TL;DR: In this paper, the authors lay theoretical foundations for new database release mechanisms that allow third-parties to construct consistent estimators of population statistics, while ensuring that the privacy of each individual contributing to the database is protected.
Proceedings ArticleDOI
Lost relatives of the Gumbel trick
TL;DR: The Gumbel trick as mentioned in this paper is a method to sample from a discrete probability distribution, or to estimate its normalizing partition function, which relies on repeatedly applying a random perturbation to the distribution in a particular way, each time solving for the most likely configuration.