Related papers: Temperature Optimization for Bayesian Deep Learnin…
Bayesian neural learning feature a rigorous approach to estimation and uncertainty quantification via the posterior distribution of weights that represent knowledge of the neural network. This not only provides point estimates of optimal…
Efficient tuning of building climate controllers to optimize occupant utility is essential for ensuring overall comfort and satisfaction. However, this is a challenging task since the latent utility are difficult to measure directly.…
Preference-based finetuning of vision--language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as \textbf{learning-dynamics--aware optimization} and…
Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquisition function such as expected improvement (EI). In practice, BO often concentrates evaluations…
Accurate thermal analysis of composites and porous media requires detailed characterization of local thermal properties in small scale. For some important applications such as lithium-ion batteries, changes in the properties during the…
Air temperature (Ta) is an essential climatological component that controls and influences various earth surface processes. In this study, we make the first attempt to employ deep learning for Ta mapping mainly based on space remote sensing…
Most environmental data come from a minority of well-monitored sites. An ongoing challenge in the environmental sciences is transferring knowledge from monitored sites to unmonitored sites. Here, we demonstrate a novel transfer learning…
Melting is a high temperature process that requires extensive sampling of configuration space, thus making melting temperature prediction computationally very expensive and challenging. Over the past few years, I have built two methods to…
The exploration of thermoelectric materials is challenging considering the large materials space, combined with added exponential degrees of freedom coming from doping and the diversity of synthetic pathways. Here we seek to incorporate…
The accurate and precise extraction of information from a modern particle physics detector, such as an electromagnetic calorimeter, may be complicated and challenging. In order to overcome the difficulties we propose processing the detector…
Bayesian neural networks that incorporate data augmentation implicitly use a ``randomly perturbed log-likelihood [which] does not have a clean interpretation as a valid likelihood function'' (Izmailov et al. 2021). Here, we provide several…
We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance, and effects. While the exact computation of various machine…
Quantifying uncertainty in weather forecasts is critical, especially for predicting extreme weather events. This is typically accomplished with ensemble prediction systems, which consist of many perturbed numerical weather simulations, or…
Generative models of complex systems often require post-hoc parameter adjustments to produce useful outputs. For example, energy-based models for protein design are sampled at an artificially low ''temperature'' to generate novel,…
The large variation of datasets is a huge barrier for image classification tasks. In this paper, we embraced this observation and introduce the finite temperature tensor network (FTTN), which imports the thermal perturbation into the matrix…
To develop intelligent receivers, automatic modulation classification (AMC) plays an important role for better spectrum utilization. The emerging deep learning (DL) technique has received much attention in AMC due to its superior…
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel…
Tensile tests at room temperature are performed using molecular dynamics on all configurations of single-walled carbon nanotubes up to 4 nm in diameter. Distributions of the Young's modulus, Poisson's ratio, ultimate tensile strength and…
Calibrating machine learning models so that predicted probabilities better reflect the true outcome frequencies is crucial for reliable decision-making across many applications. In Federated Learning (FL), the goal is to train a global…
Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from…