Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity

We study the problem of online sequential decision-making given auxiliary demonstrations from experts who made their decisions based on unobserved contextual information. These demonstrations can be viewed as solving related but slightly different tasks than what the learner faces. This setting arises in many application domains, such as self-driving cars, healthcare, and finance, where expert demonstrations are made using contextual information, which is not recorded in the data available to the learning agent. We model the problem as a zero-shot meta-reinforcement learning setting with an unknown task distribution and a Bayesian regret minimization objective, where the unobserved tasks are encoded as parameters with an unknown prior. We propose the Experts-as-Priors algorithm (ExPerior), a non-parametric empirical Bayes approach that utilizes the principle of maximum entropy to establish an informative prior over the learner's decision-making problem. This prior enables the application of any Bayesian approach for online decision-making, such as posterior sampling. We demonstrate that our strategy surpasses existing behaviour cloning and online algorithms for multi-armed bandits and reinforcement learning, showcasing the utility of our approach in leveraging expert demonstrations across different decision-making setups.

On Inference Stability for Diffusion Models

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between timesteps, limiting the model's performance in generating images effectively. Notably, we theoretically point out that this issue can be caused by the cumulative estimation gap between the predicted and the actual trajectory. To minimize that gap, we propose a novel \textit{sequence-aware} loss that aims to reduce the estimation gap to enhance the sampling quality. Furthermore, we theoretically show that our proposed loss function is a tighter upper bound of the estimation loss in comparison with the conventional loss in DPMs. Experimental results on several benchmark datasets including CIFAR10, CelebA, and CelebA-HQ consistently show a remarkable improvement of our proposed method regarding the image generalization quality measured by FID and Inception Score compared to several DPM baselines. Our code and pre-trained checkpoints are available at \url{https://github.com/viettmab/SA-DPM}.

Individual Tree Detection in Large-Scale Urban Environments using High-Resolution Multispectral Imagery

We introduce a novel deep learning method for detection of individual trees in urban environments using high-resolution multispectral aerial imagery. We use a convolutional neural network to regress a confidence map indicating the locations of individual trees, which are localized using a peak finding algorithm. Our method provides complete spatial coverage by detecting trees in both public and private spaces, and can scale to very large areas. In our study area spanning five cities in Southern California, we achieved an F-score of 0.735 and an RMSE of 2.157 m. We used our method to produce a map of all trees in the urban forest of California, indicating the potential for our method to support future urban forestry studies at unprecedented scales.

Human Imperceptible Attacks and Applications to Improve Fairness

Modern neural networks are able to perform at least as well as humans in numerous tasks involving object classification and image generation. However, small perturbations which are imperceptible to humans may significantly degrade the performance of well-trained deep neural networks. We provide a Distributionally Robust Optimization (DRO) framework which integrates human-based image quality assessment methods to design optimal attacks that are imperceptible to humans but significantly damaging to deep neural networks. Through extensive experiments, we show that our attack algorithm generates better-quality (less perceptible to humans) attacks than other state-of-the-art human imperceptible attack methods. Moreover, we demonstrate that DRO training using our optimally designed human imperceptible attacks can improve group fairness in image classification. Towards the end, we provide an algorithmic implementation to speed up DRO training significantly, which could be of independent interest.

Improvement in Machine Translation with Generative Adversarial Networks

In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. We take inspiration from RelGAN, a model for text generation, and NMT-GAN, an adversarial machine translation model, to implement a model that learns to transform awkward, non-fluent English sentences to fluent ones, while only being trained on monolingual corpora. We utilize a parameter $\lambda$ to control the amount of deviation from the input sentence, i.e. a trade-off between keeping the original tokens and modifying it to be more fluent. Our results improved upon phrase-based machine translation in some cases. Especially, GAN with a transformer generator shows some promising results. We suggests some directions for future works to build upon this proof-of-concept.

Randomized Exploration for Reinforcement Learning with General Value Function Approximation

We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) based approaches, which are often computationally intractable, our algorithm drives exploration by simply perturbing the training data with judiciously chosen i.i.d. scalar noises. To attain optimistic value function estimation without resorting to a UCB-style bonus, we introduce an optimistic reward sampling procedure. When the value functions can be represented by a function class $\mathcal{F}$, our algorithm achieves a worst-case regret bound of $\widetilde{O}(\mathrm{poly}(d_EH)\sqrt{T})$ where $T$ is the time elapsed, $H$ is the planning horizon and $d_E$ is the $\textit{eluder dimension}$ of $\mathcal{F}$. In the linear setting, our algorithm reduces to LSVI-PHE, a variant of RLSVI, that enjoys an $\widetilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret. We complement the theory with an empirical evaluation across known difficult exploration tasks.