Search Results for author:
Found 6 papers, 3 papers with code
Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models.
Fast and Correct Gradient-Based Optimisation for Probabilistic Programming via Smoothing
Thus we can prove stochastic gradient descent with the reparameterisation gradient estimator to be correct when applied to the smoothed problem.
Densities of Almost Surely Terminating Probabilistic Programs are Differentiable Almost Everywhere
We give SPCF a sampling-style operational semantics a la Borgstrom et al., and study the associated weight (commonly referred to as the density) function and value function on the set of possible execution traces.
Defunctionalization of Higher-Order Constrained Horn Clauses
In addition to well-sortedness of the algorithm's output, we prove that if an input HoCHC is solvable, then the result of its defunctionalization is solvable.
Programming Languages D.2.4; F.3.1; F.4.1
Higher-Order Constrained Horn Clauses and Refinement Types
Motivated by applications in automated verification of higher-order functional programs, we develop a notion of constrained Horn clauses in higher-order logic and a decision problem concerning their satisfiability.
Programming Languages Logic in Computer Science D.2.4; F.3.1; F.4.1
Unboundedness and Downward Closures of Higher-Order Pushdown Automata
We show the diagonal problem for higher-order pushdown automata (HOPDA), and hence the simultaneous unboundedness problem, is decidable.
Formal Languages and Automata Theory F.4.3
