Pascal Jutras-Dubé

Pascal Jutras-Dubé, Mohammad B. Al-Khasawneh, Zhichao Yang et al.

Population synthesis involves generating synthetic yet realistic representations of a target population of micro-agents for behavioral modeling and simulation. Traditional methods, often reliant on target population samples, such as census data or travel surveys, face limitations due to high costs and small sample sizes, particularly at smaller geographical scales. We propose a novel framework based on copulas to generate synthetic data for target populations where only empirical marginal distributions are known. This method utilizes samples from different populations with similar marginal dependencies, introduces a spatial component into population synthesis, and considers various information sources for more realistic generators. Concretely, the process involves normalizing the data and treating it as realizations of a given copula, and then training a generative model before incorporating the information on the marginals of the target population. Utilizing American Community Survey data, we assess our framework's performance through standardized root mean squared error (SRMSE) and so-called sampled zeros. We focus on its capacity to transfer a model learned from one population to another. Our experiments include transfer tests between regions at the same geographical level as well as to lower geographical levels, hence evaluating the framework's adaptability in varied spatial contexts. We compare Bayesian Networks, Variational Autoencoders, and Generative Adversarial Networks, both individually and combined with our copula framework. Results show that the copula enhances machine learning methods in matching the marginals of the reference data. Furthermore, it consistently surpasses Iterative Proportional Fitting in terms of SRMSE in the transferability experiments, while introducing unique observations not found in the original training sample.

Hrishikesh Viswanath, Aneesh Bhattacharya, Pascal Jutras-Dubé et al.

Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding vectors and global style tokens to capture emotions, these models represent emotions as a component of style or represent them in discrete categories. We propose AffectEcho, an emotion translation model, that uses a Vector Quantized codebook to model emotions within a quantized space featuring five levels of affect intensity to capture complex nuances and subtle differences in the same emotion. The quantized emotional embeddings are implicitly derived from spoken speech samples, eliminating the need for one-hot vectors or explicit strength embeddings. Experimental results demonstrate the effectiveness of our approach in controlling the emotions of generated speech while preserving identity, style, and emotional cadence unique to each speaker. We showcase the language-independent emotion modeling capability of the quantized emotional embeddings learned from a bilingual (English and Chinese) speech corpus with an emotion transfer task from a reference speech to a target speech. We achieve state-of-art results on both qualitative and quantitative metrics.

Pascal Jutras-Dubé, Ruqi Zhang, Aniket Bera

Planning with generative models has emerged as an effective decision-making paradigm across a wide range of domains, including reinforcement learning and autonomous navigation. While continuous replanning at each timestep might seem intuitive because it allows decisions to be made based on the most recent environmental observations, it results in substantial computational challenges, primarily due to the complexity of the generative model's underlying deep learning architecture. Our work addresses this challenge by introducing a simple adaptive planning policy that leverages the generative model's ability to predict long-horizon state trajectories, enabling the execution of multiple actions consecutively without the need for immediate replanning. We propose to use the predictive uncertainty derived from a Deep Ensemble of inverse dynamics models to dynamically adjust the intervals between planning sessions. In our experiments conducted on locomotion tasks within the OpenAI Gym framework, we demonstrate that our adaptive planning policy allows for a reduction in replanning frequency to only about 10% of the steps without compromising the performance. Our results underscore the potential of generative modeling as an efficient and effective tool for decision-making.

Vineet Punyamoorty, Pascal Jutras-Dubé, Ruqi Zhang et al.

By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories in deterministic environments, they face challenges in dynamic settings with moving obstacles. Effective collision avoidance demands continuous monitoring and adaptive decision-making. While replanning at every timestep could ensure safety, it introduces substantial computational overhead due to the repetitive prediction of overlapping state sequences -- a process that is particularly costly with diffusion models, known for their intensive iterative sampling procedure. We propose an adaptive generative planning approach that dynamically adjusts replanning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant replanning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and a 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates and an improved ability to navigate the environment safely.

Pascal Jutras-Dubé, Patrick Pynadath, Ruqi Zhang

Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high computational costs that limit their practicality in time-sensitive or resource-constrained settings. In this work, we introduce consistent diffusion samplers, a new class of samplers designed to generate high-fidelity samples in a single step. We first develop a distillation algorithm to train a consistent diffusion sampler from a pretrained diffusion model without pre-collecting large datasets of samples. Our algorithm leverages incomplete sampling trajectories and noisy intermediate states directly from the diffusion process. We further propose a method to train a consistent diffusion sampler from scratch, fully amortizing exploration by training a single model that both performs diffusion sampling and skips intermediate steps using a self-consistency loss. Through extensive experiments on a variety of unnormalized distributions, we show that our approach yields high-fidelity samples using less than 1% of the network evaluations required by traditional diffusion samplers.