183 citations · 387 across the 16 of their papers we have counts for
6 papers · 1 filter
Approximations in Probabilistic Programs
Ekansh Sharma, Daniel M. Roy
We study the first-order probabilistic programming language introduced by Staton et al. (2016), but with an additional language construct, , that, like the fixpoint…
Linear Mode Connectivity and the Lottery Ticket Hypothesis
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy +1
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that st…
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite +2
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and recently extended by Bu, Zou, and Veeravalli…
Black-box constructions for exchangeable sequences of random multisets
Creighton Heaukulani, Daniel M. Roy
We develop constructions for exchangeable sequences of point processes that are rendered conditionally-i.i.d. negative binomial processes by a (possibly unknown) random measure cal…
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
Jun Yang, Shengyang Sun, Daniel M. Roy
The developments of Rademacher complexity and PAC-Bayesian theory have been largely independent. One exception is the PAC-Bayes theorem of Kakade, Sridharan, and Tewari (2008), whi…
Stabilizing the Lottery Ticket Hypothesis
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy +1
Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have…