This work studies post-training parameter quantization in large language...
While diffusion models excel at generating high-quality samples, their l...
Propensity scores are commonly used to balance observed covariates while...
Accurately estimating uncertainty is a crucial component of decision-mak...
Language models have demonstrated the ability to generate highly fluent ...
Normalizing flows are a popular approach for constructing probabilistic ...
Embedding discrete solvers as differentiable layers has given modern dee...
Recent advances in deep learning have been driven by large-scale paramet...
Accounting for the effects of confounders is one of the central challeng...
Predictive uncertainties can be characterized by two properties–calibrat...
Modern classification algorithms are susceptible to adversarial
examples...
Numerous applications of machine learning involve predicting flexible
pr...
Bayesian optimization is a procedure that allows obtaining the global op...
Learning representations that accurately capture long-range dependencies...
Estimates of predictive uncertainty are important for accurate model-bas...
Methods for reasoning under uncertainty are a key building block of accu...
Constraint-based learning reduces the burden of collecting labels by hav...
Many problems in machine learning are naturally expressed in the languag...
We introduce a new audio processing technique that increases the samplin...
Tensor factorization arises in many machine learning applications, such
...
Although many algorithms for the multi-armed bandit problem are
well-und...