6 papers
Scaling of learning time for high dimensional inputs
Carlos Stein Brito
Representation learning from complex data typically involves models with a large number of parameters, which in turn require large amounts of data samples. In neural network models…
Direct Learning of Calibration-Aware Uncertainty for Neural PDE Surrogates
Carlos Stein Brito
Neural PDE surrogates are often deployed in data-limited or partially observed regimes where downstream decisions depend on calibrated uncertainty in addition to low prediction err…
Precise Bayesian Neural Networks
Carlos Stein Brito
Despite its long history, Bayesian neural networks (BNNs) and variational training remain underused in practice: standard Gaussian posteriors misalign with network geometry, KL ter…
Twin-Boot: Uncertainty-Aware Optimization via Online Two-Sample Bootstrapping
Carlos Stein Brito
Standard gradient descent methods yield point estimates with no measure of confidence. This limitation is acute in overparameterized and low-data regimes, where models have many pa…
Cross-regularization: Adaptive Model Complexity through Validation Gradients
Carlos Stein Brito
Model regularization requires extensive manual tuning to balance complexity against overfitting. Cross-regularization resolves this tradeoff by directly adapting regularization par…
World Models as Reference Trajectories for Rapid Motor Adaptation
Carlos Stein Brito, Daniel McNamee
Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrain…