arXiv subjects

Isaac Tamblyn

Publications and source records attributed to Isaac Tamblyn.

At least 19 recordsLinked to original sources

arXiv2025

Benchmark control problems in nonequilibrium statistical mechanics

We present a set of computer codes designed to test methods for optimizing time-dependent control protocols in fluctuating nonequilibrium systems. Each problem consists of a stochastic model, an optimization objective, and C++ and Python implementations that can be run on Unix-like systems. These benchmark systems are simple enough to run on a laptop, but challenging enough to test the capabilities of modern optimization methods. This release includes five problems and a worked example. The problem set is called NESTbench25, for NonEquilibrium STatistical mechanics benchmarks (2025).

cond-mat.stat-mech↗

arXiv2024

Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning

Reinforcement learning (RL) has been shown to learn sophisticated control policies for complex tasks including games, robotics, heating and cooling systems and text generation. The action-perception cycle in RL, however, generally assumes that a measurement of the state of the environment is available at each time step without a cost. In applications such as materials design, deep-sea and planetary robot exploration and medicine, however, there can be a high cost associated with measuring, or even approximating, the state of the environment. In this paper, we survey the recently growing literature that adopts the perspective that an RL agent might not need, or even want, a costly measurement at each time step. Within this context, we propose the Deep Dynamic Multi-Step Observationless Agent (DMSOA), contrast it with the literature and empirically evaluate it on OpenAI gym and Atari Pong environments. Our results, show that DMSOA learns a better policy with fewer decision steps and measurements than the considered alternative from the literature.

cs.LG↗

arXiv2023

Automatic graph representation algorithm for heterogeneous catalysis

One of the most appealing aspects of machine learning for material design is its high throughput exploration of chemical spaces, but to reach the ceiling of ML-aided exploration, more than current model architectures and processing algorithms are required. New architectures such as Graph Neural Networks (GNNs) have seen significant research investments recently. For heterogeneous catalysis, defining substrate intramolecular bonds and adsorbate/substrate intermolecular bonds is a time-consuming and challenging process. Before applying a model, dataset pre-processing, node/bond descriptor design, and specific model constraints have to be considered. In this work, a framework designed to solve these issues is presented in the form of an automatic graph representation algorithm (AGRA) tool to extract the local chemical environment of metallic surface adsorption sites is presented. This tool is able to gather multiple adsorption geometry datasets composed of different systems and combine them into a single model. To show AGRA's excellent transferability and reduced computational cost compared to other graph representation methods, it was applied to 5 different catalytic reaction datasets and benchmarked against the Open Catalyst Projects (OCP) graph representation method. The two ORR datasets with O/OH adsorbates obtained 0.053 eV RMSD when combined together, whereas the three CO2RR datasets with CHO/CO/COOH obtained an average performance of 0.088 eV RMSD. To further display the algorithm's versatility and extrapolation ability, a model was trained on a subset combination of all 5 datasets with an RMSD of 0.105 eV. This universal model was then used to predict a wide range of adsorption energies and an entirely new ORR catalyst system and then verified through Density Functional Theory calculations

cond-mat.mtrl-sci↗

arXiv2023

ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry

This paper provides a simulated laboratory for making use of Reinforcement Learning (RL) for chemical discovery. Since RL is fairly data intensive, training agents `on-the-fly' by taking actions in the real world is infeasible and possibly dangerous. Moreover, chemical processing and discovery involves challenges which are not commonly found in RL benchmarks and therefore offer a rich space to work in. We introduce a set of highly customizable and open-source RL environments, ChemGymRL, based on the standard Open AI Gym template. ChemGymRL supports a series of interconnected virtual chemical benches where RL agents can operate and train. The paper introduces and details each of these benches using well-known chemical reactions as illustrative examples, and trains a set of standard RL algorithms in each of these benches. Finally, discussion and comparison of the performances of several standard RL methods are provided in addition to a list of directions for future work as a vision for the further development and usage of ChemGymRL.

cs.LG↗

arXiv2023

fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems

We discuss our simulation tool, fintech-kMC, which is designed to generate synthetic data for machine learning model development and testing. fintech-kMC is an agent-based model driven by a kinetic Monte Carlo (a.k.a. continuous time Monte Carlo) engine which simulates the behaviour of customers using an online digital financial platform. The tool provides an interpretable, reproducible, and realistic way of generating synthetic data which can be used to validate and test AI/ML models and pipelines to be used in real-world customer-facing financial applications.

cs.LG↗

arXiv2022

Machine Learning Diffusion Monte Carlo Energies

We present two machine learning methodologies that are capable of predicting diffusion Monte Carlo (DMC) energies with small datasets (~60 DMC calculations in total). The first uses voxel deep neural networks (VDNNs) to predict DMC energy densities using Kohn-Sham density functional theory (DFT) electron densities as input. The second uses kernel ridge regression (KRR) to predict atomic contributions to the DMC total energy using atomic environment vectors as input (we used atom centred symmetry functions, atomic environment vectors from the ANI models, and smooth overlap of atomic positions). We first compare the methodologies on pristine graphene lattices, where we find the KRR methodology performs best in comparison to gradient boosted decision trees, random forest, gaussian process regression, and multilayer perceptrons. In addition, KRR outperforms VDNNs by an order of magnitude. Afterwards, we study the generalizability of KRR to predict the energy barrier associated with a Stone-Wales defect. Lastly, we move from 2D to 3D materials and use KRR to predict total energies of liquid water. In all cases, we find that the KRR models are more accurate than Kohn-Sham DFT and all mean absolute errors are less than chemical accuracy.

cond-mat.mes-hall↗

arXiv2022

Training neural networks using Metropolis Monte Carlo and an adaptive variant

We examine the zero-temperature Metropolis Monte Carlo algorithm as a tool for training a neural network by minimizing a loss function. We find that, as expected on theoretical grounds and shown empirically by other authors, Metropolis Monte Carlo can train a neural net with an accuracy comparable to that of gradient descent, if not necessarily as quickly. The Metropolis algorithm does not fail automatically when the number of parameters of a neural network is large. It can fail when a neural network's structure or neuron activations are strongly heterogenous, and we introduce an adaptive Monte Carlo algorithm, aMC, to overcome these limitations. The intrinsic stochasticity and numerical stability of the Monte Carlo method allow aMC to train deep neural networks and recurrent neural networks in which the gradient is too small or too large to allow training by gradient descent. Monte Carlo methods offer a complement to gradient-based methods for training neural networks, allowing access to a distinct set of network architectures and principles.

cs.LG↗

arXiv2022

Cellular automata can classify data by inducing trajectory phase coexistence

We show that cellular automata can classify data by inducing a form of dynamical phase coexistence. We use Monte Carlo methods to search for general two-dimensional deterministic automata that classify images on the basis of activity, the number of state changes that occur in a trajectory initiated from the image. When the number of timesteps of the automaton is a trainable parameter, the search scheme identifies automata that generate a population of dynamical trajectories displaying high or low activity, depending on initial conditions. Automata of this nature behave as nonlinear activation functions with an output that is effectively binary, resembling an emergent version of a spiking neuron.

cs.NE↗

arXiv2022

Dynamic programming with incomplete information to overcome navigational uncertainty in a nautical environment

Using a novel toy nautical navigation environment, we show that dynamic programming can be used when only incomplete information about a partially observed Markov decision process (POMDP) is known. By incorporating uncertainty into our model, we show that navigation policies can be constructed that maintain safety, outperforming the baseline performance of traditional dynamic programming for Markov decision processes (MDPs). Adding in controlled sensing methods, we show that these policies can also lower measurement costs at the same time.

math.OC↗

arXiv2022

Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning

The use of reinforcement learning (RL) in scientific applications, such as materials design and automated chemistry, is increasing. A major challenge, however, lies in fact that measuring the state of the system is often costly and time consuming in scientific applications, whereas policy learning with RL requires a measurement after each time step. In this work, we make the measurement costs explicit in the form of a costed reward and propose a framework that enables off-the-shelf deep RL algorithms to learn a policy for both selecting actions and determining whether or not to measure the current state of the system at each time step. In this way, the agents learn to balance the need for information with the cost of information. Our results show that when trained under this regime, the Dueling DQN and PPO agents can learn optimal action policies whilst making up to 50\% fewer state measurements, and recurrent neural networks can produce a greater than 50\% reduction in measurements. We postulate the these reduction can help to lower the barrier to applying RL to real-world scientific applications.

cs.LG↗

arXiv2022

Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge

Deploying generative machine learning techniques to generate novel chemical structures based on molecular fingerprint representation has been well established in molecular design. Typically, sequential learning (SL) schemes such as hidden Markov models (HMM) and, more recently, in the sequential deep learning context, recurrent neural network (RNN) and long short-term memory (LSTM) were used extensively as generative models to discover unprecedented molecules. To this end, emission probability between two states of atoms plays a central role without considering specific chemical or physical properties. Lack of supervised domain knowledge can mislead the learning procedure to be relatively biased to the prevalent molecules observed in the training data that are not necessarily of interest. We alleviated this drawback by augmenting the training data with domain knowledge, e.g. quantitative estimates of the drug-likeness score (QEDs). As such, our experiments demonstrated that with this subtle trick called enriched sequential learning (ESL), specific patterns of particular interest can be learnt better, which led to generating de novo molecules with ameliorated QEDs.

q-bio.BM↗

arXiv2022

Learning stochastic dynamics and predicting emergent behavior using transformers

We show that a neural network originally designed for language processing can learn the dynamical rules of a stochastic system by observation of a single dynamical trajectory of the system, and can accurately predict its emergent behavior under conditions not observed during training. We consider a lattice model of active matter undergoing continuous-time Monte Carlo dynamics, simulated at a density at which its steady state comprises small, dispersed clusters. We train a neural network called a transformer on a single trajectory of the model. The transformer, which we show has the capacity to represent dynamical rules that are numerous and nonlocal, learns that the dynamics of this model consists of a small number of processes. Forward-propagated trajectories of the trained transformer, at densities not encountered during training, exhibit motility-induced phase separation and so predict the existence of a nonequilibrium phase transition. Transformers have the flexibility to learn dynamical rules from observation without explicit enumeration of rates or coarse-graining of configuration space, and so the procedure used here can be applied to a wide range of physical systems, including those with large and complex dynamical generators.

cond-mat.stat-mech↗

arXiv2022

Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning

We use voxel deep neural networks to predict energy densities and functional derivatives of electron kinetic energies for the Thomas-Fermi model and Kohn-Sham density functional theory calculations. We show that the ground-state electron density can be found via direct minimization for a graphene lattice without any projection scheme using a voxel deep neural network trained with the Thomas-Fermi model. Additionally, we predict the kinetic energy of a graphene lattice within chemical accuracy after training from only 2 Kohn-Sham density functional theory (DFT) calculations. We identify an important sampling issue inherent in Kohn-Sham DFT calculations and propose future work to rectify this problem. Furthermore, we demonstrate an alternative, functional derivative-free, Monte Carlo based orbital free density functional theory algorithm to calculate an accurate 2-electron density in a double inverted Gaussian potential with a machine-learned kinetic energy functional.

cond-mat.mes-hall↗

arXiv2021

Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning

Using a model heat engine, we show that neural network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally-efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.

cs.NE↗

arXiv2021

Golem: An algorithm for robust experiment and process optimization

Numerous challenges in science and engineering can be framed as optimization tasks, including the maximization of reaction yields, the optimization of molecular and materials properties, and the fine-tuning of automated hardware protocols. Design of experiment and optimization algorithms are often adopted to solve these tasks efficiently. Increasingly, these experiment planning strategies are coupled with automated hardware to enable autonomous experimental platforms. The vast majority of the strategies used, however, do not consider robustness against the variability of experiment and process conditions. In fact, it is generally assumed that these parameters are exact and reproducible. Yet some experiments may have considerable noise associated with some of their conditions, and process parameters optimized under precise control may be applied in the future under variable operating conditions. In either scenario, the optimal solutions found might not be robust against input variability, affecting the reproducibility of results and returning suboptimal performance in practice. Here, we introduce Golem, an algorithm that is agnostic to the choice of experiment planning strategy and that enables robust experiment and process optimization. Golem identifies optimal solutions that are robust to input uncertainty, thus ensuring the reproducible performance of optimized experimental protocols and processes. It can be used to analyze the robustness of past experiments, or to guide experiment planning algorithms toward robust solutions on the fly. We assess the performance and domain of applicability of Golem through extensive benchmark studies and demonstrate its practical relevance by optimizing an analytical chemistry protocol under the presence of significant noise in its experimental conditions.

math.OC↗

arXiv2021

Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning

Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free technique for biomedical and mineralogical imaging which can suffer from low signal to noise ratios. Here we demonstrate the use of an unsupervised deep learning neural network for rapid and automatic denoising of SRS images: UHRED (Unsupervised Hyperspectral Resolution Enhancement and Denoising). UHRED is capable of one-shot learning; only one hyperspectral image is needed, with no requirements for training on previously labelled datasets or images. Furthermore, by applying a k-means clustering algorithm to the processed data, we demonstrate automatic, unsupervised image segmentation, yielding, without prior knowledge of the sample, intuitive chemical species maps, as shown here for a lithium ore sample.

eess.SP↗

arXiv2021

Correspondence between neuroevolution and gradient descent

We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise. Averaged over independent realizations of the learning process, neuroevolution is equivalent to gradient descent on the loss function. We use numerical simulation to show that this correspondence can be observed for finite mutations,for shallow and deep neural networks. Our results provide a connection between two families of neural-network training methods that are usually considered to be fundamentally different.

cs.NE↗

arXiv2021

Electronic Response Quantities of Solids and Deep Learning

We introduce a deep neural network (DNN) framework called the \textbf{r}eal-space \textbf{a}tomic \textbf{d}ecomposition \textbf{net}work (\textsc{radnet}), which is capable of making accurate polarization and static dielectric function predictions for solids. We use these predictions to calculate Born-effective charges, longitudinal optical transverse optical (LO-TO) splitting frequencies, and Raman tensors for two prototypical examples: GaAs and BN. We then compute the Raman spectra, and find excellent agreement with \textit{ab initio} techniques. \textsc{radnet} is as good or better than current methodologies. Lastly, we discuss how \textsc{radnet} scales to larger systems, paving the way for predictions of response functions on meso-scale structures with \textit{ab initio} accuracy.

cond-mat.mes-hall↗