1 citations · 1 across the 9 of their papers we have counts for
9 papers
Nikodým maximal function with restricted directions
Tuomas Orponen, Hrit Roy
We study the planar Nikodým maximal operator associated to a direction set . We show that the quasi-Assouad dimension $s := \dim_{\math…
VIKING: Deep variational inference with stochastic projections
Samuel G. Fadel, Hrittik Roy, Nicholas Krämer +5
Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality p…
Matrix-Free Least Squares Solvers: Values, Gradients, and What to Do With Them
Hrittik Roy, Søren Hauberg, Nicholas Krämer
This paper argues that the method of least squares has significant unfulfilled potential in modern machine learning, far beyond merely being a tool for fitting linear models. To re…
Uniform decoupling for convex curves
Hrit Roy
Using a high/low argument, we prove a universal decoupling estimate with constant for general convex curves in the plane. These curves have no additional regul…
Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections
Marco Miani, Hrittik Roy, Søren Hauberg
Bayesian deep learning all too often underfits so that the Bayesian prediction is less accurate than a simple point estimate. Uncertainty quantification then comes at the cost of a…
Reparameterization invariance in approximate Bayesian inference
Hrittik Roy, Marco Miani, Carl Henrik Ek +4
Current approximate posteriors in Bayesian neural networks (BNNs) exhibit a crucial limitation: they fail to maintain invariance under reparameterization, i.e. BNNs assign differen…
Gradients of Functions of Large Matrices
Nicholas Krämer, Pablo Moreno-Muñoz, Hrittik Roy +1
Tuning scientific and probabilistic machine learning models for example, partial differential equations, Gaussian processes, or Bayesian neural networks often relies on eva…
Improved bounds for Bochner--Riesz operators associated with rough convex domains in the plane
Hrit Roy
We consider generalized Bochner-Riesz operators associated with planar convex domains. We construct domains which yield improved bounds for the Bochner-Riesz over previous re…
On the curvature of the loss landscape
Alison Pouplin, Hrittik Roy, Sidak Pal Singh +1
One of the main challenges in modern deep learning is to understand why such over-parameterized models perform so well when trained on finite data. A way to analyze this generaliza…