Related papers: Learning to Condition: A Neural Heuristic for Scal…

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into…

Several approaches to graphically representing context-specific relations among jointly distributed categorical variables have been proposed, along with structure learning algorithms. While existing optimization-based methods have limited…

Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a…

Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…

The global push to advance Carbon Capture and Sequestration initiatives and green energy solutions, such as geothermal, have thrust new demands upon the current state-of-the-art subsurface fluid simulators. The requirement to be able to…

Understanding model's sensitivity to its training data is crucial but can also be challenging and costly, especially during training. To simplify such issues, we present the Memory-Perturbation Equation (MPE) which relates model's…

We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost. The framework of conditional variational autoencoders describes a class of methods to tackle…

In this paper, we propose a novel hierarchical framework for robot navigation in dynamic environments with heterogeneous constraints. Our approach leverages a graph neural network trained via reinforcement learning (RL) to efficiently…

Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant…

This thesis studies two problems in modern statistics. First, we study selective inference, or inference for hypothesis that are chosen after looking at the data. The motiving application is inference for regression coefficients selected by…

Learning parameters of latent graphical models (GM) is inherently much harder than that of no-latent ones since the latent variables make the corresponding log-likelihood non-concave. Nevertheless, expectation-maximization schemes are…

In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors. Our strategy is to find an inner approximation of the set of admissible policy parameters,…

Accuracy in neural PDE solvers often breaks down not because of limited expressivity, but due to poor optimisation caused by ill-conditioning, especially in multi-fidelity and stiff problems. We study this issue in Physics-Informed Extreme…

The rapid adoption of complex Artificial Intelligence (AI) and Machine Learning (ML) models has led to their characterization as black boxes due to the difficulty of explaining their internal decision-making processes. This lack of…

Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while learning and select the correct set during inference.…

Nonlinear model predictive control (MPC) is a flexible and increasingly popular framework used to synthesize feedback control strategies that can satisfy both state and control input constraints. In this framework, an optimization problem,…

Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long…

We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient descent) to quickly solve parametric convex optimization…

When the training and test data are from different distributions, domain adaptation is needed to reduce dataset bias to improve the model's generalization ability. Since it is difficult to directly match the cross-domain joint…