Search Results for author:
Found 8 papers, 3 papers with code
Expressive Power of ReLU and Step Networks under Floating-Point Operations
In this work, we analyze the expressive power of neural networks under a more realistic setup: when we use floating-point numbers and operations.
Training with Mixed-Precision Floating-Point Assignments
Hence, it is important to use a precision assignment -- a mapping from all tensors (arising in training) to precision levels (high or low) -- that keeps most of the tensors in low precision and leads to sufficiently accurate models.
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
For a neural network with bias parameters, we first prove that the incorrect set is always empty.
Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference
We present a static analysis for discovering differentiable or more generally smooth parts of a given probabilistic program, and show how the analysis can be used to improve the pathwise gradient estimator, one of the most popular methods for posterior inference and model learning.
On Correctness of Automatic Differentiation for Non-Differentiable Functions
For these PAP functions, we propose a new type of derivatives, called intensional derivatives, and prove that these derivatives always exist and coincide with standard derivatives for almost all inputs.
Differentiable Algorithm for Marginalising Changepoints
We present an algorithm for marginalising changepoints in time-series models that assume a fixed number of unknown changepoints.
Towards Verified Stochastic Variational Inference for Probabilistic Programs
In this paper, we analyse one of the most fundamental and versatile variational inference algorithms, called score estimator, using tools from denotational semantics and program analysis.
Reparameterization Gradient for Non-differentiable Models
We tackle the challenge by generalizing the reparameterization trick, one of the most effective techniques for addressing the variance issue for differentiable models, so that the trick works for non-differentiable models as well.
