no code implementations • 20 Jun 2022 • Bohdan Kivva, Goutham Rajendran, Pradeep Ravikumar, Bryon Aragam
We prove identifiability of a broad class of deep latent variable models that (a) have universal approximation capabilities and (b) are the decoders of variational autoencoders that are commonly used in practice.
no code implementations • NeurIPS 2021 • Goutham Rajendran, Bohdan Kivva, Ming Gao, Bryon Aragam
Greedy algorithms have long been a workhorse for learning graphical models, and more broadly for learning statistical models with sparse structure.
1 code implementation • NeurIPS 2021 • Bohdan Kivva, Goutham Rajendran, Pradeep Ravikumar, Bryon Aragam
We study the problem of reconstructing a causal graphical model from data in the presence of latent variables.
no code implementations • 9 Mar 2021 • Bohdan Kivva
At MFCS'77, Valiant introduced matrix rigidity as a tool to prove circuit lower bounds for linear functions and since then this notion received much attention and found applications in other areas of complexity theory.
Data Structures and Algorithms Computational Complexity Combinatorics
no code implementations • 18 Nov 2020 • Bohdan Kivva, Aaron Potechin
In this paper we show that simple semidefinite programs inspired by degree $4$ SOS can exactly solve the tensor nuclear norm, tensor decomposition, and tensor completion problems on tensors with random asymmetric components.