Search Results for author: Alexander Shmakov

Found 12 papers, 3 papers with code

RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels

no code implementations5 Oct 2023 Alexander Shmakov, Avisek Naug, Vineet Gundecha, Sahand Ghorbanpour, Ricardo Luna Gutierrez, Ashwin Ramesh Babu, Antonio Guillen, Soumyendu Sarkar

In this paper, we combine recent developments in Deep Kernel Learning (DKL) and attention-based Transformer models to improve the modeling powers of GP surrogates with meta-learning.

Bayesian Optimization Meta-Learning +2

Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks

no code implementations5 Sep 2023 Michael James Fenton, Alexander Shmakov, Hideki Okawa, Yuji Li, Ko-Yang Hsiao, Shih-Chieh Hsu, Daniel Whiteson, Pierre Baldi

We explore the performance of the extended capability of Spa-Net in the context of semi-leptonic decays of top quark pairs as well as top quark pairs produced in association with a Higgs boson.

Single Particle Analysis

Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers

no code implementations10 Mar 2023 Alexander Shmakov, Alejandro Yankelevich, Jianming Bian, Pierre Baldi

TransformerCVN classifies events with 90\% accuracy and improves the reconstruction of individual particles by 6\% over baseline methods which lack the integrated architecture of TransformerCVN.

Deep Learning Models of the Discrete Component of the Galactic Interstellar Gamma-Ray Emission

no code implementations6 Jun 2022 Alexander Shmakov, Mohammadamin Tavakoli, Pierre Baldi, Christopher M. Karwin, Alex Broughton, Simona Murgia

A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky.

Rxn Hypergraph: a Hypergraph Attention Model for Chemical Reaction Representation

no code implementations2 Jan 2022 Mohammadamin Tavakoli, Alexander Shmakov, Francesco Ceccarelli, Pierre Baldi

To achieve such skills, it is important to develop good representations of chemical reactions, or good deep learning architectures that can learn such representations automatically from the data.

Property Prediction

SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention

1 code implementation7 Jun 2021 Alexander Shmakov, Michael James Fenton, Ta-Wei Ho, Shih-Chieh Hsu, Daniel Whiteson, Pierre Baldi

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics.

A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks

no code implementations8 Feb 2021 Forest Agostinelli, Alexander Shmakov, Stephen Mcaleer, Roy Fox, Pierre Baldi

We use Q* search to solve the Rubik's cube when formulated with a large action space that includes 1872 meta-actions and find that this 157-fold increase in the size of the action space incurs less than a 4-fold increase in computation time and less than a 3-fold increase in number of nodes generated when performing Q* search.

Rubik's Cube

Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks

1 code implementation19 Oct 2020 Michael James Fenton, Alexander Shmakov, Ta-Wei Ho, Shih-Chieh Hsu, Daniel Whiteson, Pierre Baldi

Top quarks, produced in large numbers at the Large Hadron Collider, have a complex detector signature and require special reconstruction techniques.

Single Particle Analysis

ColosseumRL: A Framework for Multiagent Reinforcement Learning in $N$-Player Games

no code implementations10 Dec 2019 Alexander Shmakov, John Lanier, Stephen Mcaleer, Rohan Achar, Cristina Lopes, Pierre Baldi

Much of recent success in multiagent reinforcement learning has been in two-player zero-sum games.

Multiagent Systems

Solving the Rubik's Cube with Approximate Policy Iteration

no code implementations ICLR 2019 Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi

Autodidactic Iteration is able to learn how to solve the Rubik’s Cube and the 15-puzzle without relying on human data.

Rubik's Cube

Solving the Rubik's Cube Without Human Knowledge

9 code implementations18 May 2018 Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi

A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision.

Combinatorial Optimization reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.