no code implementations • 4 Apr 2024 • Min Jae Song
We show that $L^2$-accurate score estimation, in the absence of strong assumptions on the data distribution, is computationally hard even when sample complexity is polynomial in the relevant problem parameters.
no code implementations • 27 Oct 2022 • Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input.
no code implementations • 7 Dec 2021 • Ilias Zadik, Min Jae Song, Alexander S. Wein, Joan Bruna
Prior work on many similar inference tasks portends that such lower bounds strongly suggest the presence of an inherent statistical-to-computational gap for clustering, that is, a parameter regime where the clustering task is statistically possible but no polynomial-time algorithm succeeds.
no code implementations • NeurIPS 2021 • Min Jae Song, Ilias Zadik, Joan Bruna
More precisely, our reduction shows that any polynomial-time algorithm (not necessarily gradient-based) for learning such functions under small noise implies a polynomial-time quantum algorithm for solving worst-case lattice problems, whose hardness form the foundation of lattice-based cryptography.
no code implementations • 11 Mar 2021 • Sungjoon Choi, Min Jae Song, Hyemin Ahn, Joohyung Kim
In this paper, we present self-supervised shared latent embedding (S3LE), a data-driven motion retargeting method that enables the generation of natural motions in humanoid robots from motion capture data or RGB videos.
no code implementations • 1 Jan 2021 • Min Jae Song, Dan Kushnir
That is, we train the embedding with respect to cosine similarity, where we define two observations to be similar if the agent can reach one observation from the other within a few steps, and define impact in terms of this similarity measure.
1 code implementation • 15 Sep 2020 • William F. Whitney, Min Jae Song, David Brandfonbrener, Jaan Altosaar, Kyunghyun Cho
We consider the problem of evaluating representations of data for use in solving a downstream task.
no code implementations • 19 May 2020 • Joan Bruna, Oded Regev, Min Jae Song, Yi Tang
We introduce a continuous analogue of the Learning with Errors (LWE) problem, which we name CLWE.