Search Results for author: Alán Aspuru-Guzik

Found 58 papers, 37 papers with code

Quantum linear algebra is all you need for Transformer architectures

no code implementations26 Feb 2024 Naixu Guo, Zhan Yu, Matthew Choi, Aman Agrawal, Kouhei Nakaji, Alán Aspuru-Guzik, Patrick Rebentrost

Generative machine learning methods such as large-language models are revolutionizing the creation of text and images.

A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?

1 code implementation7 Feb 2024 Agustinus Kristiadi, Felix Strieth-Kalthoff, Marta Skreta, Pascal Poupart, Alán Aspuru-Guzik, Geoff Pleiss

Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space.

Bayesian Optimization Efficient Exploration

ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization

no code implementations13 Jan 2024 Kourosh Darvish, Marta Skreta, Yuchi Zhao, Naruki Yoshikawa, Sagnik Som, Miroslav Bogdanovic, Yang Cao, Han Hao, Haoping Xu, Alán Aspuru-Guzik, Animesh Garg, Florian Shkurti

Despite the many benefits incurred by the integration of advanced and special-purpose lab equipment, many aspects of experimentation are still manually conducted by chemists, for example, polishing an electrode in electrochemistry experiments.


nach0: Multimodal Natural and Chemical Languages Foundation Model

1 code implementation21 Nov 2023 Micha Livne, Zulfat Miftahutdinov, Elena Tutubalina, Maksim Kuznetsov, Daniil Polykovskiy, Annika Brundyn, Aastha Jhunjhunwala, Anthony Costa, Alex Aliper, Alán Aspuru-Guzik, Alex Zhavoronkov

Large Language Models (LLMs) have substantially driven scientific progress in various domains, and many papers have demonstrated their ability to tackle complex problems with creative solutions.

Decoder named-entity-recognition +2

Towards equilibrium molecular conformation generation with GFlowNets

no code implementations20 Oct 2023 Alexandra Volokhova, Michał Koziarski, Alex Hernández-García, Cheng-Hao Liu, Santiago Miret, Pablo Lemos, Luca Thiede, Zichao Yan, Alán Aspuru-Guzik, Yoshua Bengio

Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule.

Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance

1 code implementation17 Oct 2023 Austin Cheng, Alston Lo, Santiago Miret, Brooks Pate, Alán Aspuru-Guzik

KREED's top-1 predictions identify the correct 3D structure with >98% accuracy on the QM9 and GEOM datasets when provided with substitution coordinates of all heavy atoms with natural isotopic abundance.

Atom-by-atom protein generation and beyond with language models

no code implementations16 Aug 2023 Daniel Flam-Shepherd, Kevin Zhu, Alán Aspuru-Guzik

However, they are constrained to generate proteins with only the set of amino acids represented in their vocabulary.

Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files

no code implementations9 May 2023 Daniel Flam-Shepherd, Alán Aspuru-Guzik

In doing so, we demonstrate that it is not necessary to use simplified molecular representations to train chemical language models -- that they are powerful generative models capable of directly exploring chemical space in three dimensions for very different structures.


Recent advances in the Self-Referencing Embedding Strings (SELFIES) library

1 code implementation7 Feb 2023 Alston Lo, Robert Pollice, AkshatKumar Nigam, Andrew D. White, Mario Krenn, Alán Aspuru-Guzik

String-based molecular representations play a crucial role in cheminformatics applications, and with the growing success of deep learning in chemistry, have been readily adopted into machine learning pipelines.

Waveflow: Enforcing boundary conditions in smooth normalizing flows with application to fermionic wave functions

no code implementations27 Nov 2022 Luca Thiede, Chong Sun, Alán Aspuru-Guzik

In this paper, we introduce four main novelties: First, we present a new way of handling the topology problem of normalizing flows.

Group SELFIES: A Robust Fragment-Based Molecular String Representation

1 code implementation23 Nov 2022 Austin Cheng, Andy Cai, Santiago Miret, Gustavo Malkomes, Mariano Phielipp, Alán Aspuru-Guzik

We introduce Group SELFIES, a molecular string representation that leverages group tokens to represent functional groups or entire substructures while maintaining chemical robustness guarantees.

Quantum compression with classically simulatable circuits

no code implementations6 Jul 2022 Abhinav Anand, Jakob S. Kottmann, Alán Aspuru-Guzik

As we continue to find applications where the currently available noisy devices exhibit an advantage over their classical counterparts, the efficient use of quantum resources is highly desirable.

Evolutionary Algorithms

On scientific understanding with artificial intelligence

no code implementations4 Apr 2022 Mario Krenn, Robert Pollice, Si Yue Guo, Matteo Aldeghi, Alba Cervera-Lierta, Pascal Friederich, Gabriel dos Passos Gomes, Florian Häse, Adrian Jinich, AkshatKumar Nigam, Zhenpeng Yao, Alán Aspuru-Guzik

Imagine an oracle that correctly predicts the outcome of every particle physics experiment, the products of every chemical reaction, or the function of every protein.


Bayesian optimization with known experimental and design constraints for chemistry applications

1 code implementation29 Mar 2022 Riley J. Hickman, Matteo Aldeghi, Florian Häse, Alán Aspuru-Guzik

The tools developed constitute a simple, yet versatile strategy to enable model-based optimization with known experimental constraints, contributing to its applicability as a core component of autonomous platforms for scientific discovery.

Bayesian Optimization

Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning

no code implementations1 Feb 2022 Daniel Flam-Shepherd, Alexander Zhigalin, Alán Aspuru-Guzik

We introduce a novel RL framework for scalable 3D design that uses a hierarchical agent to build molecules by placing molecular substructures sequentially in 3D space, thus attempting to build on the existing human knowledge in the field of molecular design.

Drug Discovery reinforcement-learning +1

Keeping it Simple: Language Models can learn Complex Molecular Distributions

1 code implementation6 Dec 2021 Daniel Flam-Shepherd, Kevin Zhu, Alán Aspuru-Guzik

In this work, we investigate the capacity of simple language models to learn distributions of molecules.

Language Modelling

Learning quantum dynamics with latent neural ODEs

1 code implementation20 Oct 2021 Matthew Choi, Daniel Flam-Shepherd, Thi Ha Kyaw, Alán Aspuru-Guzik

The core objective of machine-assisted scientific discovery is to learn physical laws from experimental data without prior knowledge of the systems in question.

Design of quantum optical experiments with logic artificial intelligence

1 code implementation27 Sep 2021 Alba Cervera-Lierta, Mario Krenn, Alán Aspuru-Guzik

In this work, we propose the use of logic AI for the design of optical quantum experiments.

Formal Logic

Gemini: Dynamic Bias Correction for Autonomous Experimentation and Molecular Simulation

1 code implementation5 Mar 2021 Riley J. Hickman, Florian Häse, Loïc M. Roch, Alán Aspuru-Guzik

We recommend using Gemini for regression tasks with sparse data and in an autonomous workflow setting where its predictions of expensive to evaluate objectives can be used to construct a more informative acquisition function, thus reducing the number of expensive evaluations an optimizer needs to achieve desired target values.

Bayesian Optimization regression

Golem: An algorithm for robust experiment and process optimization

1 code implementation5 Mar 2021 Matteo Aldeghi, Florian Häse, Riley J. Hickman, Isaac Tamblyn, Alán Aspuru-Guzik

Design of experiment and optimization algorithms are often adopted to solve these tasks efficiently.

Assigning Confidence to Molecular Property Prediction

1 code implementation23 Feb 2021 AkshatKumar Nigam, Robert Pollice, Matthew F. D. Hurley, Riley J. Hickman, Matteo Aldeghi, Naruki Yoshikawa, Seyone Chithrananda, Vincent A. Voelz, Alán Aspuru-Guzik

Introduction: Computational modeling has rapidly advanced over the last decades, especially to predict molecular properties for chemistry, material science and drug design.

Molecular Docking Molecular Property Prediction +1

Natural Evolutionary Strategies for Variational Quantum Computation

no code implementations30 Nov 2020 Abhinav Anand, Matthias Degroote, Alán Aspuru-Guzik

We implement two specific approaches, the exponential and separable natural evolutionary strategies, for parameter optimization of PQCs and compare them against standard gradient descent.

A Feasible Approach for Automatically Differentiable Unitary Coupled-Cluster on Quantum Computers

1 code implementation11 Nov 2020 Jakob S. Kottmann, Abhinav Anand, Alán Aspuru-Guzik

We show that, within our framework, the gradient of an expectation value with respect to a parameterized n-fold fermionic excitation can be evaluated by four expectation values of similar form and size, whereas most standard approaches based on the direct application of the parameter-shift-rule come with an associated cost of O(2^(2n)) expectation values.

Quantum Physics Chemical Physics Computational Physics

Tequila: A platform for rapid development of quantum algorithms

4 code implementations5 Nov 2020 Jakob S. Kottmann, Sumner Alperin-Lea, Teresa Tamayo-Mendoza, Alba Cervera-Lierta, Cyrille Lavigne, Tzu-Ching Yen, Vladyslav Verteletskyi, Philipp Schleich, Abhinav Anand, Matthias Degroote, Skylar Chaney, Maha Kesibi, Artur F. Izmaylov, Alán Aspuru-Guzik

As in classical computing, heuristics play a crucial role in the development of new quantum algorithms, resulting in high demand for flexible and reliable ways to implement, test, and share new ideas.

Quantum Physics Chemical Physics Computational Physics

Olympus: a benchmarking framework for noisy optimization and experiment planning

1 code implementation8 Oct 2020 Florian Häse, Matteo Aldeghi, Riley J. Hickman, Loïc M. Roch, Melodie Christensen, Elena Liles, Jason E. Hein, Alán Aspuru-Guzik

Experiment planning strategies based on off-the-shelf optimization algorithms can be employed in fully autonomous research platforms to achieve desired experimentation goals with the minimum number of trials.

Benchmarking Probabilistic Deep Learning

The Meta-Variational Quantum Eigensolver (Meta-VQE): Learning energy profiles of parameterized Hamiltonians for quantum simulation

3 code implementations28 Sep 2020 Alba Cervera-Lierta, Jakob S. Kottmann, Alán Aspuru-Guzik

We present the meta-VQE, an algorithm capable to learn the ground state energy profile of a parametrized Hamiltonian.

Quantum Physics

Reducing qubit requirements while maintaining numerical precision for the Variational Quantum Eigensolver: A Basis-Set-Free Approach

1 code implementation6 Aug 2020 Jakob S. Kottmann, Philipp Schleich, Teresa Tamayo-Mendoza, Alán Aspuru-Guzik

We present a basis-set-free approach to the variational quantum eigensolver using an adaptive representation of the spatial part of molecular wavefunctions.

Quantum Physics Chemical Physics Computational Physics

Quantum Computer-Aided design of Quantum Optics Hardware

2 code implementations4 Jun 2020 Jakob S. Kottmann, Mario Krenn, Thi Ha Kyaw, Sumner Alperin-Lea, Alán Aspuru-Guzik

It is not clear how the full potential of large quantum systems can be exploited.

Quantum Physics Computational Physics Optics

Conceptual understanding through efficient inverse-design of quantum optical experiments

no code implementations13 May 2020 Mario Krenn, Jakob Kottmann, Nora Tischler, Alán Aspuru-Guzik

Here we present Theseus, an efficient algorithm for the design of quantum experiments, which we use to solve several open questions in experimental quantum optics.

Quantum Physics Optics

Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge

no code implementations26 Mar 2020 Florian Häse, Matteo Aldeghi, Riley J. Hickman, Loïc M. Roch, Alán Aspuru-Guzik

Leveraging domain knowledge in the form of physicochemical descriptors, Gryffin can significantly accelerate the search for promising molecules and materials.

Bayesian Optimization Density Estimation

Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules

no code implementations23 Oct 2019 Benjamin Sanchez-Lengeling, Jennifer N. Wei, Brian K. Lee, Richard C. Gerkin, Alán Aspuru-Guzik, Alexander B. Wiltschko

Based on these early results with graph neural networks for molecular properties, we hope machine learning can eventually do for olfaction what it has already done for vision and hearing.

BIG-bench Machine Learning Nutrition +1

Beyond Ternary OPV: High-Throughput Experimentation and Self-Driving Laboratories Optimize Multi-Component Systems

1 code implementation8 Sep 2019 Stefan Langner, Florian Häse, José Darío Perea, Tobias Stubhan, Jens Hauch, Loïc M. Roch, Thomas Heumueller, Alán Aspuru-Guzik, Christoph J. Brabec

Fundamental advances to increase the efficiency as well as stability of organic photovoltaics (OPVs) are achieved by designing ternary blends which represents a clear trend towards multi-component active layer blends.

Applied Physics

An Artificial Spiking Quantum Neuron

no code implementations14 Jul 2019 Lasse Bjørn Kristensen, Matthias Degroote, Peter Wittek, Alán Aspuru-Guzik, Nikolaj T. Zinner

Artificial spiking neural networks have found applications in areas where the temporal nature of activation offers an advantage, such as time series prediction and signal processing.

Time Series Time Series Prediction

Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation

2 code implementations31 May 2019 Mario Krenn, Florian Häse, AkshatKumar Nigam, Pascal Friederich, Alán Aspuru-Guzik

SELFIES can be directly applied in arbitrary machine learning models without the adaptation of the models; each of the generated molecule candidates is valid.

molecular representation valid

Quantum Chemistry in the Age of Quantum Computing

9 code implementations24 Dec 2018 Yudong Cao, Jonathan Romero, Jonathan P. Olson, Matthias Degroote, Peter D. Johnson, Mária Kieferová, Ian D. Kivlichan, Tim Menke, Borja Peropadre, Nicolas P. D. Sawaya, Sukin Sim, Libor Veis, Alán Aspuru-Guzik

Practical challenges in simulating quantum systems on classical computers have been widely recognized in the quantum physics and quantum chemistry communities over the past century.

Quantum Physics

Variational Quantum Factoring

2 code implementations27 Aug 2018 Eric R. Anschuetz, Jonathan P. Olson, Alán Aspuru-Guzik, Yudong Cao

In this work, we revisit the problem of factoring, developing an alternative to Shor's algorithm, which employs established techniques to map the factoring problem to the ground state of an Ising Hamiltonian.

Quantum Physics

PHOENICS: A universal deep Bayesian optimizer

1 code implementation4 Jan 2018 Florian Häse, Loïc M. Roch, Christoph Kreisbeck, Alán Aspuru-Guzik

In this work we introduce PHOENICS, a probabilistic global optimization algorithm combining ideas from Bayesian optimization with concepts from Bayesian kernel density estimation.

Bayesian Optimization Density Estimation +1

Quantum Neuron: an elementary building block for machine learning on quantum computers

2 code implementations30 Nov 2017 Yudong Cao, Gian Giacomo Guerreschi, Alán Aspuru-Guzik

In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately.

BIG-bench Machine Learning Quantum Machine Learning

Automatic differentiation in quantum chemistry with an application to fully variational Hartree-Fock

1 code implementation22 Nov 2017 Teresa Tamayo-Mendoza, Christoph Kreisbeck, Roland Lindh, Alán Aspuru-Guzik

Automatic Differentiation (AD) is a powerful tool that allows calculating derivatives of implemented algorithms with respect to all of their parameters up to machine precision, without the need to explicitly add any additional functions.

Chemical Physics

QVECTOR: an algorithm for device-tailored quantum error correction

1 code implementation7 Nov 2017 Peter D. Johnson, Jonathan Romero, Jonathan Olson, Yudong Cao, Alán Aspuru-Guzik

Current approaches to fault-tolerant quantum computation will not enable useful quantum computation on near-term devices of 50 to 100 qubits.

Quantum Physics

Machine Learning for Quantum Dynamics: Deep Learning of Excitation Energy Transfer Properties

no code implementations20 Jul 2017 Florian Häse, Christoph Kreisbeck, Alán Aspuru-Guzik

Understanding the relationship between the structure of light-harvesting systems and their excitation energy transfer properties is of fundamental importance in many applications including the development of next generation photovoltaics.

BIG-bench Machine Learning

Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models

1 code implementation30 May 2017 Gabriel Lima Guimaraes, Benjamin Sanchez-Lengeling, Carlos Outeiral, Pedro Luis Cunha Farias, Alán Aspuru-Guzik

In unsupervised data generation tasks, besides the generation of a sample based on previous observations, one would often like to give hints to the model in order to bias the generation towards desirable metrics.

 Ranked #1 on Molecular Graph Generation on ZINC (QED Top-3 metric)

Molecular Graph Generation Music Generation +1

Neural networks for the prediction organic chemistry reactions

no code implementations22 Aug 2016 Jennifer N. Wei, David Duvenaud, Alán Aspuru-Guzik

Reaction prediction remains one of the major challenges for organic chemistry, and is a pre-requisite for efficient synthetic planning.

qHiPSTER: The Quantum High Performance Software Testing Environment

4 code implementations26 Jan 2016 Mikhail Smelyanskiy, Nicolas P. D. Sawaya, Alán Aspuru-Guzik

We present qHiPSTER, the Quantum High Performance Software Testing Environment.

Quantum Physics Distributed, Parallel, and Cluster Computing

Exploiting locality in quantum computation for quantum chemistry

1 code implementation29 Jul 2014 Jarrod R. McClean, Ryan Babbush, Peter J. Love, Alán Aspuru-Guzik

Accurate prediction of chemical and material properties from first principles quantum chemistry is a challenging task on traditional computers.

Quantum Physics Chemical Physics

A variational eigenvalue solver on a quantum processor

no code implementations10 Apr 2013 Alberto Peruzzo, Jarrod McClean, Peter Shadbolt, Man-Hong Yung, Xiao-Qi Zhou, Peter J. Love, Alán Aspuru-Guzik, Jeremy L. O'Brien

Quantum computers promise to efficiently solve important problems that are intractable on a conventional computer.

Quantum Physics Chemical Physics

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