Biodiversity is declining globally at an unprecedented rate. Managers urgently need to allocate limited resources to control pest species where interventions have the highest ecological impact. However, many species are hard to detect, and data collection is often expensive, irregular, and incomplete, thus posing significant challenges for machine learning models that traditionally require large and regular datasets. We present a novel deep learning architecture that estimates the spatiotemporal abundance of hard-to-detect species from sparse, zero-inflated, and irregular data. Our method combines Graph Convolutional Networks (GCNs) to model spatial dependencies across monitoring sites with Recurrent Neural Networks (RNNs) to capture long-range temporal dynamics explicitly addresses the challenges of data sparsity, heterogeneity, and irregular sampling. We apply our model to the Crown-of-Thorns Starfish (COTS) on Australia's Great Barrier Reef, a species with devastating impact on coral reefs and a major target of pest control programs. Our method significantly outperforms baseline approaches and the current resource-intensive approach, manta-tow surveillance, in both accuracy and detectability. Simulations indicate a 20% increase in starfish removal efficiency over a year, enabling more effective coral protection. This work demonstrates how tailored deep learning methods can overcome ecological data limitations and substantially improve conservation outcomes.

A key challenge in automated formal reasoning is the intractable search space, which grows exponentially with the depth of the proof. This branching is caused by the large number of candidate proof tactics which can be applied to a given goal. Nonetheless, many of these tactics are semantically similar or lead to an execution error, wasting valuable resources in both cases. We address the problem of effectively pruning this search, using only synthetic data generated from previous proof attempts. We first demonstrate that it is possible to generate semantically aware tactic representations which capture the effect on the proving environment, likelihood of success, and execution time. We then propose a novel filtering mechanism which leverages these representations to select semantically diverse and high quality tactics, using Determinantal Point Processes. Our approach, 3D-Prover, is designed to be general, and to augment any underlying tactic generator. We demonstrate the effectiveness of 3D-Prover on the miniF2F and LeanDojo benchmarks by augmenting popular open source proving LLMs. We show that our approach leads to an increase in the overall proof rate, as well as a significant improvement in the tactic success rate, execution time and diversity. We make our code available at https://github.com/sean-lamont/3D-Prover.

Artificial Intelligence for Theorem Proving (AITP) has given rise to a plethora of benchmarks and methodologies, particularly in Interactive Theorem Proving (ITP). Research in the area is fragmented, with a diverse set of approaches being spread across several ITP systems. This presents a significant challenge to the comparison of methods, which are often complex and difficult to replicate. Addressing this, we present BAIT, a framework for the fair and streamlined comparison of learning approaches in ITP. We demonstrate BAIT’s capabilities with an in-depth comparison, across several ITP benchmarks, of state-of-the-art architectures applied to the problem of formula embedding. We find that Structure Aware Transformers perform particularly well, improving on techniques associated with the original problem sets. BAIT also allows us to assess the end-to-end proving performance of systems built on interactive environments. This unified perspective reveals a novel end-to-end system that improves on prior work. We also provide a qualitative analysis, illustrating that improved performance is associated with more semantically-aware embeddings. By streamlining the implementation and comparison of Machine Learning algorithms in the ITP context, we anticipate BAIT will be a springboard for future research.

Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such as Bayesian Optimisation (BO) are ill-equipped to handle such mixed-variable search spaces. The optimisation breadth introduced by categorical variables in the mixed-input setting has seen recent approaches operating on local trust regions, but these methods can be greedy in suboptimal regions of the search space. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We develop a tree-based method which retains a global view of the optimisation spaces by identifying regions in the search space with high potential candidates which we call value proposals. Our method uses these proposals to make selections on both the categorical and continuous components of the input. We show that this approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.

We study the problem of imputing missing values in a dataset, which has important applications in many domains. The key to missing value imputation is to capture the data distribution with incomplete samples and impute the missing values accordingly. In this paper, by leveraging the fact that any two batches of data with missing values come from the same data distribution, we propose to impute the missing values of two batches of samples by transforming them into a latent space through deep invertible functions and matching them distributionally. To learn the transformations and impute the missing values simultaneously, a simple and well-motivated algorithm is proposed. Our algorithm has fewer hyperparameters to fine-tune and generates high-quality imputations regardless of how missing values are generated. Extensive experiments over a large number of datasets and competing benchmark algorithms show that our method achieves state-of-the-art performance.

Sparse linear models are one of several core tools for interpretable machine learning, a field of emerging importance as predictive models permeate decision-making in many domains. Unfortunately, sparse linear models are far less flexible as functions of their input features than black-box models like deep neural networks. With this capability gap in mind, we study a not-uncommon situation where the input features dichotomize into two groups: explanatory features, which are candidates for inclusion as variables in an interpretable model, and contextual features, which select from the candidate variables and determine their effects. This dichotomy leads us to the contextual lasso, a new statistical estimator that fits a sparse linear model to the explanatory features such that the sparsity pattern and coefficients vary as a function of the contextual features. The fitting process learns this function nonparametrically via a deep neural network. To attain sparse coefficients, we train the network with a novel lasso regularizer in the form of a projection layer that maps the network's output onto the space of $\ell_1$-constrained linear models. An extensive suite of experiments on real and synthetic data suggests that the learned models, which remain highly transparent, can be sparser than the regular lasso without sacrificing the predictive power of a standard deep neural network.

Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches practical, by training a parameterized policy that proposes designs efficiently at deployment time. However, these methods may not sufficiently explore the design space, require access to a differentiable probabilistic model and can only optimize over continuous design spaces. Here, we address these limitations by showing that the problem of optimizing policies can be reduced to solving a Markov decision process (MDP). We solve the equivalent MDP with modern deep reinforcement learning techniques. Our experiments show that our approach is also computationally efficient at deployment time and exhibits state-of-the-art performance on both continuous and discrete design spaces, even when the probabilistic model is a black box.

One of the most important and challenging application areas for complex machine learning methods is to predict, characterize and model rich, multi-dimensional, neural data. Recent advances in neural recording techniques have made it possible to monitor the activity of a large number of neurons across different brain regions as animals perform behavioural tasks. This poses the critical challenge of establishing links between neural activity at a microscopic scale, which might for instance represent sensory input, and at a macroscopic scale, which then generates behaviour. Predominant modeling methods apply rather disjoint techniques to these scales; by contrast, we suggest an end-to-end model which exploits recent developments of flexible, but tractable, neural network point-process models to characterize dependencies between stimuli, actions, and neural data. We apply this model to a public dataset collected using Neuropixel probes in mice performing a visually-guided behavioural task as well as a synthetic dataset produced from a hierarchical network model with reciprocally connected sensory and integration circuits intended to characterize animal behaviour in a fixed-duration motion discrimination task. We show that our model outperforms previous approaches and contributes novel insights into the relationships between neural activity and behaviour.

We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. The proposed framework is able to learn proof search strategies as well as tactic and arguments prediction in an end-to-end manner. We formulate the process of ITP as a Markov decision process (MDP) in which each state represents a set of potential derivation paths. This structure allows us to introduce a novel backtracking mechanism which enables the agent to efficiently discard (predicted) dead-end derivations and restart the derivation from promising alternatives. We implement the framework in the HOL theorem prover. Experimental results show that the framework using learned search strategies outperforms existing automated theorem provers (i.e., hammers) available in HOL when evaluated on unseen problems. We further elaborate the role of key components of the framework using ablation studies.

Individual characteristics in human decision-making are often quantified by fitting a parametric cognitive model to subjects' behavior and then studying differences between them in the associated parameter space. However, these models often fit behavior more poorly than recurrent neural networks (RNNs), which are more flexible and make fewer assumptions about the underlying decision-making processes. Unfortunately, the parameter and latent activity spaces of RNNs are generally high-dimensional and uninterpretable, making it hard to use them to study individual differences. Here, we show how to benefit from the flexibility of RNNs while representing individual differences in a low-dimensional and interpretable space. To achieve this, we propose a novel end-to-end learning framework in which an encoder is trained to map the behavior of subjects into a low-dimensional latent space. These low-dimensional representations are used to generate the parameters of individual RNNs corresponding to the decision-making process of each subject. We introduce terms into the loss function that ensure that the latent dimensions are informative and disentangled, i.e., encouraged to have distinct effects on behavior. This allows them to align with separate facets of individual differences. We illustrate the performance of our framework on synthetic data as well as a dataset including the behavior of patients with psychiatric disorders.

We develop an automated variational method for inference in models with Gaussian process (GP) priors and general likelihoods. The method supports multiple outputs and multiple latent functions and does not require detailed knowledge of the conditional likelihood, only needing its evaluation as a black-box function. Using a mixture of Gaussians as the variational distribution, we show that the evidence lower bound and its gradients can be estimated efficiently using samples from univariate Gaussian distributions. Furthermore, the method is scalable to large datasets which is achieved by using an augmented prior via the inducing-variable approach underpinning most sparse GP approximations, along with parallel computation and stochastic optimization. We evaluate our approach quantitatively and qualitatively with experiments on small datasets, medium-scale datasets and large datasets, showing its competitiveness under different likelihood models and sparsity levels. On the large-scale experiments involving prediction of airline delays and classification of handwritten digits, we show that our method is on par with the state-of-the-art hard-coded approaches for scalable GP regression and classification.

State-space and action representations form the building blocks of decision-making processes in the brain; states map external cues to the current situation of the agent whereas actions provide the set of motor commands from which the agent can choose to achieve specific goals. Although these factors differ across environments, it is currently unknown whether or how accurately state and action representations are acquired by the agent because previous experiments have typically provided this information a priori through instruction or pre-training. Here we studied how state and action representations adapt to reflect the structure of the world when such a priori knowledge is not available. We used a sequential decision-making task in rats in which they were required to pass through multiple states before reaching the goal, and for which the number of states and how they map onto external cues were unknown a priori. We found that, early in training, animals selected actions as if the task was not sequential and outcomes were the immediate consequence of the most proximal action. During the course of training, however, rats recovered the true structure of the environment and made decisions based on the expanded state-space, reflecting the multiple stages of the task. Similarly, we found that the set of actions expanded with training, although the emergence of new action sequences was sensitive to the experimental parameters and specifics of the training procedure. We conclude that the profile of choices shows a gradual shift from simple representations to more complex structures compatible with the structure of the world.

Popular computational models of decision-making make specific assumptions about learning processes that may cause them to underfit observed behaviours. Here we suggest an alternative method using recurrent neural networks (RNNs) to generate a flexible family of models that have sufficient capacity to represent the complex learning and decision- making strategies used by humans. In this approach, an RNN is trained to predict the next action that a subject will take in a decision-making task and, in this way, learns to imitate the processes underlying subjects' choices and their learning abilities. We demonstrate the benefits of this approach using a new dataset drawn from patients with either unipolar (n = 34) or bipolar (n = 33) depression and matched healthy controls (n = 34) making decisions on a two-armed bandit task. The results indicate that this new approach is better than baseline reinforcement-learning methods in terms of overall performance and its capacity to predict subjects' choices. We show that the model can be interpreted using off-policy simulations and thereby provides a novel clustering of subjects' learning processes-something that often eludes traditional approaches to modelling and behavioural analysis.

Computational modeling plays an important role in modern neuroscience research. Much previous research has relied on statistical methods, separately, to address two problems that are actually interdependent. First, given a particular computational model, Bayesian hierarchical techniques have been used to estimate individual variation in parameters over a population of subjects, leveraging their population-level distributions. Second, candidate models are themselves compared, and individual variation in the expressed model estimated, according to the fits of the models to each subject. The interdependence between these two problems arises because the relevant population for estimating parameters of a model depends on which other subjects express the model. Here, we propose a hierarchical Bayesian inference (HBI) framework for concurrent model comparison, parameter estimation and inference at the population level, combining previous approaches. We show that this framework has important advantages for both parameter estimation and model comparison theoretically and experimentally. The parameters estimated by the HBI show smaller errors compared to other methods. Model comparison by HBI is robust against outliers and is not biased towards overly simplistic models. Furthermore, the fully Bayesian approach of our theory enables researchers to make inference on group-level parameters by performing HBI t-test.

Evaluating the future consequences of actions is achievable by simulating a mental search tree into the future. Expanding deep trees, however, is computationally taxing. Therefore, machines and humans use a plan-until-habit scheme that simulates the environment up to a limited depth and then exploits habitual values as proxies for consequences that may arise in the future. Two outstanding questions in this scheme are "in which directions the search tree should be expanded?", and "when should the expansion stop?". Here we propose a principled solution to these questions based on a speed/accuracy tradeoff: deeper expansion in the appropriate directions leads to more accurate planning, but at the cost of slower decision-making. Our simulation results show how this algorithm expands the search tree effectively and efficiently in a grid-world environment. We further show that our algorithm can explain several behavioral patterns in animals and humans, namely the effect of time-pressure on the depth of planning, the effect of reward magnitudes on the direction of planning, and the gradual shift from goal-directed to habitual behavior over the course of training. The algorithm also provides several predictions testable in animal/human experiments.

Traditional methods for the discovery of latent network structures are limited in two ways: they either assume that all the signal comes from the network (i.e. there is no source of signal outside the network) or they place constraints on the network parameters to ensure model or algorithmic stability. We address these limitations by proposing a model that incorporates a Gaussian process prior on a network-independent component and formally proving that we get algorithmic stability for free while providing a novel perspective on model stability as well as robustness results and precise intervals for key inference parameters. We show that, on three applications, our approach outperforms previous methods consistently.

Neuroscience studies of human decision-making abilities commonly involve subjects completing a decision-making task while BOLD signals are recorded using fMRI. Hypotheses are tested about which brain regions mediate the effect of past experience, such as rewards, on future actions. One standard approach to this is model-based fMRI data analysis, in which a model is fitted to the behavioral data, i.e., a subject's choices, and then the neural data are parsed to find brain regions whose BOLD signals are related to the model's internal signals. However, the internal mechanics of such purely behavioral models are not constrained by the neural data, and therefore might miss or mischaracterize aspects of the brain. To address this limitation, we introduce a new method using recurrent neural network models that are flexible enough to be jointly fitted to the behavioral and neural data. We trained a model so that its internal states were suitably related to neural activity during the task, while at the same time its output predicted the next action a subject would execute. We then used the fitted model to create a novel visualization of the relationship between the activity in brain regions at different times following a reward and the choices the subject subsequently made. Finally, we validated our method using a previously published dataset. We found that the model was able to recover the underlying neural substrates that were discovered by explicit model engineering in the previous work, and also derived new results regarding the temporal pattern of brain activity.

We develop an automated variational inference method for Bayesian structured prediction problems with Gaussian process (GP) priors and linear-chain likelihoods. Our approach does not need to know the details of the structured likelihood model and can scale up to a large number of observations. Furthermore, we show that the required expected likelihood term and its gradients in the variational objective (ELBO) can be estimated efficiently by using expectations over very low-dimensional Gaussian distributions. Optimization of the ELBO is fully parallelizable over sequences and amenable to stochastic optimization, which we use along with control variate techniques to make our framework useful in practice. Results on a set of natural language processing tasks show that our method can be as good as (and sometimes better than, in particular with respect to expected log-likelihood) hard-coded approaches including SVM-struct and CRF, and overcomes the scalability limitations of previous inference algorithms based on sampling. Overall, this is a fundamental step to developing automated inference methods for Bayesian structured prediction.

We propose a sparse method for scalable automated variational inference (AVI) in a large class of models with Gaussian process (GP) priors, multiple latent functions, multiple outputs and non-linear likelihoods. Our approach maintains the statistical efficiency property of the original AVI method, requiring only expectations over univariate Gaussian distributions to approximate the posterior with a mixture of Gaussians. Experiments on small datasets for various problems including regression, classification, Log Gaussian Cox processes, and warped GPs show that our method can perform as well as the full method under high levels of sparsity. On larger experiments using the MNIST and the SARCOS datasets we show that our method can provide superior performance to previously published scalable approaches that have been handcrafted to specific likelihood models.

Behavioral evidence suggests that instrumental conditioning is governed by two forms of action control: a goal-directed and a habit learning process. Model-based reinforcement learning (RL) has been argued to underlie the goal-directed process; however, the way in which it interacts with habits and the structure of the habitual process has remained unclear. According to a flat architecture, the habitual process corresponds to model-free RL, and its interaction with the goal-directed process is coordinated by an external arbitration mechanism. Alternatively, the interaction between these systems has recently been argued to be hierarchical, such that the formation of action sequences underlies habit learning and a goal-directed process selects between goal-directed actions and habitual sequences of actions to reach the goal. Here we used a two-stage decision-making task to test predictions from these accounts. The hierarchical account predicts that, because they are tied to each other as an action sequence, selecting a habitual action in the first stage will be followed by a habitual action in the second stage, whereas the flat account predicts that the statuses of the first and second stage actions are independent of each other. We found, based on subjects' choices and reaction times, that human subjects combined single actions to build action sequences and that the formation of such action sequences was sufficient to explain habitual actions. Furthermore, based on Bayesian model comparison, a family of hierarchical RL models, assuming a hierarchical interaction between habit and goal-directed processes, provided a better fit of the subjects' behavior than a family of flat models. Although these findings do not rule out all possible model-free accounts of instrumental conditioning, they do show such accounts are not necessary to explain habitual actions and provide a new basis for understanding how goal-directed and habitual action control interact.

Instrumental responses are hypothesized to be of two kinds: habitual and goal-directed, mediated by the sensorimotor and the associative cortico-basal ganglia circuits, respectively. The existence of the two heterogeneous associative learning mechanisms can be hypothesized to arise from the comparative advantages that they have at different stages of learning. In this paper, we assume that the goal-directed system is behaviourally flexible, but slow in choice selection. The habitual system, in contrast, is fast in responding, but inflexible in adapting its behavioural strategy to new conditions. Based on these assumptions and using the computational theory of reinforcement learning, we propose a normative model for arbitration between the two processes that makes an approximately optimal balance between search-time and accuracy in decision making. Behaviourally, the model can explain experimental evidence on behavioural sensitivity to outcome at the early stages of learning, but insensitivity at the later stages. It also explains that when two choices with equal incentive values are available concurrently, the behaviour remains outcome-sensitive, even after extensive training. Moreover, the model can explain choice reaction time variations during the course of learning, as well as the experimental observation that as the number of choices increases, the reaction time also increases. Neurobiologically, by assuming that phasic and tonic activities of midbrain dopamine neurons carry the reward prediction error and the average reward signals used by the model, respectively, the model predicts that whereas phasic dopamine indirectly affects behaviour through reinforcing stimulus-response associations, tonic dopamine can directly affect behaviour through manipulating the competition between the habitual and the goal-directed systems and thus, affect reaction time.

Clinical and experimental observations show individual differences in the development of addiction. Increasing evidence supports the hypothesis that dopamine receptor availability in the nucleus accumbens (NAc) predisposes drug reinforcement. Here, modeling striatal-midbrain dopaminergic circuit, we propose a reinforcement learning model for addiction based on the actor-critic model of striatum. Modeling dopamine receptors in the NAc as modulators of learning rate for appetitive--but not aversive--stimuli in the critic--but not the actor--we define vulnerability to addiction as a relatively lower learning rate for the appetitive stimuli, compared to aversive stimuli, in the critic. We hypothesize that an imbalance in this learning parameter used by appetitive and aversive learning systems can result in addiction. We elucidate that the interaction between the degree of individual vulnerability and the duration of exposure to drug has two progressive consequences: deterioration of the imbalance and establishment of an abnormal habitual response in the actor. Using computational language, the proposed model describes how development of compulsive behavior can be a function of both degree of drug exposure and individual vulnerability. Moreover, the model describes how involvement of the dorsal striatum in addiction can be augmented progressively. The model also interprets other forms of addiction, such as obesity and pathological gambling, in a common mechanism with drug addiction. Finally, the model provides an answer for the question of why behavioral addictions are triggered in Parkinson's disease patients by D2 dopamine agonist treatments.

Based on the dopamine hypotheses of cocaine addiction and the assumption of decrement of brain reward system sensitivity after long-term drug exposure, we propose a computational model for cocaine addiction. Utilizing average reward temporal difference reinforcement learning, we incorporate the elevation of basal reward threshold after long-term drug exposure into the model of drug addiction proposed by Redish. Our model is consistent with the animal models of drug seeking under punishment. In the case of nondrug reward, the model explains increased impulsivity after long-term drug exposure. Furthermore, the existence of a blocking effect for cocaine is predicted by our model.