Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the Teacher) to guide the training of the primary amortized sampler (the Student) by prioritizing high-loss regions. The Teacher, an auxiliary behavior model, is trained to sample high-error regions of the Student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage.

Causal models seek to unravel the cause-effect relationships among variables from observed data, as opposed to mere mappings among them, as traditional regression models do. This paper introduces a novel causal discovery algorithm designed for settings in which variables exhibit linearly sparse relationships. In such scenarios, the causal links represented by directed acyclic graphs (DAGs) can be encapsulated in a structural matrix. The proposed approach leverages the structural matrix's ability to reconstruct data and the statistical properties it imposes on the data to identify the correct structural matrix. This method does not rely on independence tests or graph fitting procedures, making it suitable for scenarios with limited training data. Simulation results demonstrate that the proposed method outperforms the well-known PC, GES, BIC exact search, and LINGAM-based methods in recovering linearly sparse causal structures.

Previously, we showed that computational mechanic's causal states -- predictively-equivalent trajectory classes for a stochastic dynamical system -- can be cast into a reproducing kernel Hilbert space. The result is a widely-applicable method that infers causal structure directly from very different kinds of observations and systems. Here, we expand this method to explicitly introduce the causal diffusion components it produces. These encode the kernel causal-state estimates as a set of coordinates in a reduced dimension space. We show how each component extracts predictive features from data and demonstrate their application on four examples: first, a simple pendulum -- an exactly solvable system; second, a molecular-dynamic trajectory of $n$-butane -- a high-dimensional system with a well-studied energy landscape; third, the monthly sunspot sequence -- the longest-running available time series of direct observations; and fourth, multi-year observations of an active crop field -- a set of heterogeneous observations of the same ecosystem taken for over a decade. In this way, we demonstrate that the empirical kernel causal-states algorithm robustly discovers predictive structures for systems with widely varying dimensionality and stochasticity.

Large-scale latent variable models require expressive continuous distributions that support efficient sampling and low-variance differentiation, achievable through the reparameterization trick. The Kumaraswamy (KS) distribution is both expressive and supports the reparameterization trick with a simple closed-form inverse CDF. Yet, its adoption remains limited. We identify and resolve numerical instabilities in the inverse CDF and log-pdf, exposing issues in libraries like PyTorch and TensorFlow. We then introduce simple and scalable latent variable models based on the KS, improving exploration-exploitation trade-offs in contextual multi-armed bandits and enhancing uncertainty quantification for link prediction with graph neural networks. Our results support the stabilized KS distribution as a core component in scalable variational models for bounded latent variables.

Gene regulation is a dynamic process that underlies all aspects of human development, disease response, and other key biological processes. The reconstruction of temporal gene regulatory networks has conventionally relied on regression analysis, graphical models, or other types of relevance networks. With the large increase in time series single-cell data, new approaches are needed to address the unique scale and nature of this data for reconstructing such networks. Here, we develop a deep neural network, Marlene, to infer dynamic graphs from time series single-cell gene expression data. Marlene constructs directed gene networks using a self-attention mechanism where the weights evolve over time using recurrent units. By employing meta learning, the model is able to recover accurate temporal networks even for rare cell types. In addition, Marlene can identify gene interactions relevant to specific biological responses, including COVID-19 immune response, fibrosis, and aging. Biological systems are dynamic, changing over time in response to various stimuli and events. To construct accurate models of biological activity during development, disease progression, treatment response, and other biological processes, it is essential to track their evolution over time (Bar-Joseph et al., 2012). Studying the regulation of these dynamic processes is key for understanding the underlying mechanisms that drive the response and for identifying potential interventions that can serve as cures for diseases (Silverman et al., 2020). Much of the research in this area is focused on the reconstruction of regulatory networks (Karlebach & Shamir, 2008; Badia-I-Mompel et al., 2023).

It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation, or severely distort the distribution of outputs. We present a method to balance the distortion of the output distribution with computational efficiency, allowing for the generation of long sequences of text with difficult-to-satisfy constraints, with less amplification of low probability outputs compared to existing methods. We show through a series of experiments that the task-specific performance of our method is comparable to methods that do not distort the output distribution, while being much more computationally efficient. Language models sometimes generate undesirable outputs, such as syntactically-incorrect code, hallucinated PII, or profanity. These conditions, which we collectively refer to as errors for the remainder of the paper, can be detected with incremental parsers, regular expression matching, or even simple substring searches. However, once detection occurs, there are several competing methods for mitigating errors in the output. One set of methods, constrained generation (Beurer-Kellner et al., 2024; Geng et al., 2024; Melcer et al., 2024), avoids errors by disabling the generation of any token that immediately leads to such an error. While this method is effective, it can lead to the amplification of low-probability outputs. Another class of methods avoids errors without any amplification of low-probability outputs, at the cost of additional computation. Rejection sampling is the simplest such method; i.e. if the output contains an error, simply generate another sample until the output is acceptable. Adaptive Sampling with Approximate Expected Futures (ASAp) (Park et al., 2024) provides a performance improvement over rejection sampling while maintaining the output distribution by effectively sampling without replacement, but there are still many situations in which it may converge too slowly. In our experiments, we show that our method obtains task-specific performance on par with ASAp, while converging significantly faster when the constraints are difficult to satisfy. We first describe autoregressive language models and their properties.

Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods, particularly differential privacy (DP), remains largely underexplored. While some works have explored differentially private AL for specialized scenarios like online learning, the fundamental challenge of combining AL with DP in standard learning settings has remained unaddressed, severely limiting AL's applicability in privacy-sensitive domains. This work addresses this gap by introducing differentially private active learning (DP-AL) for standard learning settings. We demonstrate that naively integrating DP-SGD training into AL presents substantial challenges in privacy budget allocation and data utilization. To overcome these challenges, we propose step amplification, which leverages individual sampling probabilities in batch creation to maximize data point participation in training steps, thus optimizing data utilization. Additionally, we investigate the effectiveness of various acquisition functions for data selection under privacy constraints, revealing that many commonly used functions become impractical. Our experiments on vision and natural language processing tasks show that DP-AL can improve performance for specific datasets and model architectures. However, our findings also highlight the limitations of AL in privacy-constrained environments, emphasizing the trade-offs between privacy, model accuracy, and data selection accuracy.

Learning a model of a stochastic setting often involves learning both general structure rules and specific properties of the instance. This paper investigates the interplay between learning the general and the specific in various learning methods, with emphasis on sample efficiency. We design a framework called {\sc LeverWorlds}, which allows the generation of simple physics-inspired worlds that follow a similar generative process with different distributions, and their instances can be expressed in natural language. These worlds allow for controlled experiments to assess the sample complexity of different learning methods. We experiment with classic learning algorithms as well as Transformer language models, both with fine-tuning and In-Context Learning (ICL). Our general finding is that (1) Transformers generally succeed in the task; but (2) they are considerably less sample efficient than classic methods that make stronger assumptions about the structure, such as Maximum Likelihood Estimation and Logistic Regression. This finding is in tension with the recent tendency to use Transformers as general-purpose estimators. We propose an approach that leverages the ICL capabilities of contemporary language models to apply simple algorithms for this type of data. Our experiments show that models currently struggle with the task but show promising potential.

Human-Robot Collaboration (HRC) has evolved into a highly promising issue owing to the latest breakthroughs in Artificial Intelligence (AI) and Human-Robot Interaction (HRI), among other reasons. This emerging growth increases the need to design multi-agent algorithms that can manage also human preferences. This paper presents an extension of the Ant Colony Optimization (ACO) meta-heuristic to solve the Minimum Time Search (MTS) task, in the case where humans and robots perform an object searching task together. The proposed model consists of two main blocks. The first one is a convolutional neural network (CNN) that provides the prior probabilities about where an object may be from a segmented image. The second one is the Sub-prior MTS-ACO algorithm (SP-MTS-ACO), which takes as inputs the prior probabilities and the particular search preferences of the agents in different sub-priors to generate search plans for all agents. The model has been tested in real experiments for the joint search of an object through a Vizanti web-based visualization in a tablet computer. The designed interface allows the communication between a human and our humanoid robot named IVO. The obtained results show an improvement in the search perception of the users without loss of efficiency.

Traditional reinforcement learning often struggles to generate diverse, high-reward solutions, especially in domains like drug design and black-box function optimization. Markov Chain Monte Carlo (MCMC) methods provide an alternative method of RL in candidate selection but suffer from high computational costs and limited candidate diversity exploration capabilities. In response, GFlowNet, a novel neural network architecture, was introduced to model complex system dynamics and generate diverse high-reward trajectories. To further enhance this approach, this paper proposes improvements to GFlowNet by introducing a new loss function and refining the training objective associated with sub-GFlowNet. These enhancements aim to integrate entropy and leverage network structure characteristics, improving both candidate diversity and computational efficiency. We demonstrated the superiority of the refined GFlowNet over traditional methods by empirical results from hypergrid experiments and molecule synthesis tasks. The findings underscore the effectiveness of incorporating entropy and exploiting network structure properties in solution generation in molecule synthesis as well as diverse experimental designs.