Search Results for author:
Found 12 papers, 0 papers with code
On computable learning of continuous features
We introduce definitions of computable PAC learning for binary classification over computable metric spaces.
Conjugate Energy-Based Models
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables.
Detecting and Exorcising Statistical Demons from Language Models with Anti-Models of Negative Data
Indeed, self-supervised language models trained on "positive" examples of English text generalize in desirable ways to many natural language tasks.
Verification of ML Systems via Reparameterization
Proof assistants can be used to formally verify machine learning systems by constructing machine checked proofs of correctness that rule out such bugs.
Unlocking Fairness: a Trade-off Revisited
The prevailing wisdom is that a model's fairness and its accuracy are in tension with one another.
Rate-Regularization and Generalization in VAEs
Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate).
A Formal Proof of PAC Learnability for Decision Stumps
We present a formal proof in Lean of probably approximately correct (PAC) learnability of the concept class of decision stumps.
Scaling Hierarchical Coreference with Homomorphic Compression
In this case, we need the representation to be a homomorphism so that the hash of unions and differences of sets can be computed directly from the hashes of operands.
Sketching for Latent Dirichlet-Categorical Models
We examine a related problem in which the parameters of a Bayesian model are very large and expensive to store in memory, and propose more compact representations of parameter values that can be used during inference.
Gradient-based Inference for Networks with Output Constraints
Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures.
Augur: Data-Parallel Probabilistic Modeling
We show that the compiler can generate data-parallel inference code scalable to thousands of GPU cores by making use of the conditional independence relationships in the Bayesian network.
Augur: a Modeling Language for Data-Parallel Probabilistic Inference
In this paper, we present a probabilistic programming language and compiler for Bayesian networks designed to make effective use of data-parallel architectures such as GPUs.
