Related papers: Project Dynamics and Emergent Complexity
Reinforcement learning in partially observed Markov decision processes (POMDPs) faces two challenges. (i) It often takes the full history to predict the future, which induces a sample complexity that scales exponentially with the horizon.…
Data-Driven Product Development (DDPD) leverages data to learn the relationship between product design specifications and resulting properties. To discover improved designs, we train a neural network on past experiments and apply Projected…
A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as Embedded Ensembling (EE); its particular examples are…
This work presents strategies to learn an Energy-Based Model (EBM) according to the desired length of its MCMC sampling trajectories. MCMC trajectories of different lengths correspond to models with different purposes. Our experiments cover…
In both high-performance computing (HPC) environments and the public cloud, the duration of time to retrieve or save your results is simultaneously unpredictable and important to your over all resource budget. It is generally accepted…
We propose enforcing constraints on Model-Based Diffusion by introducing emerging barrier functions inspired by interior point methods. We demonstrate that the standard Model-Based Diffusion algorithm can lead to catastrophic performance…
Automated synthesis of correct-by-construction controllers for autonomous systems is crucial for their deployment in safety-critical scenarios. Such autonomous systems are naturally modeled as stochastic dynamical models. The general…
This paper introduces a novel end-to-end framework that efficiently integrates data quality assessment with machine learning (ML) model operations in real-time production environments. While existing approaches treat data quality assessment…
The distribution of block maxima of sequences of independent and identically-distributed random variables is used to model extreme values in many disciplines. The traditional extreme value (EV) theory derives a closed-form expression for…
Robotic tasks which involve uncertainty--due to variation in goal, environment configuration, or confidence in task model--may require human input to instruct or adapt the robot. In tasks with physical contact, several existing methods for…
Model predictive control (MPC) of hybrid dynamical systems is challenging because the associated optimization problem is nonsmooth and the resulting feedback law is discontinuous. This paper develops real-time MPC algorithms for nonlinear…
In this work, we introduce the Equivariance Seeker Model (ESM), a data-driven method for discovering the underlying finite equivariant symmetry group of an arbitrary function. ESM achieves this by optimizing a loss function that balances…
Model predictive control (MPC) has emerged as an effective strategy for water distribution systems (WDSs) management. However, it is hampered by the computational burden for large-scale WDSs due to the combinatorial growth of possible…
Energy-based models (EBM) have become increasingly popular within computer vision. EBMs bring a probabilistic approach to training deep neural networks (DNN) and have been shown to enhance performance in areas such as calibration,…
Variability in multiple independent input parameters makes it difficult to estimate the resultant variability in the system's overall response. The Propagation of Errors and Monte-Carlo techniques are two major methods to predict the…
A characteristic of existing predictive process monitoring techniques is to first construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating…
Nowadays, we are witnessing the advent of the Internet of Things (EC) with numerous devices performing interactions between them or with end users. The huge number of devices leads to huge volumes of collected data that demand the…
The conventional von Neumann architecture has been revealed as a major performance and energy bottleneck for rising data-intensive applications. %, due to the intensive data movements. The decade-old idea of leveraging in-memory processing…
The recent increase in data availability and reliability has led to a surge in the development of learning-based model predictive control (MPC) frameworks for robot systems. Despite attaining substantial performance improvements over their…
Endowing deep models with the ability to generalize in dynamic scenarios is of vital significance for real-world deployment, given the continuous and complex changes in data distribution. Recently, evolving domain generalization (EDG) has…