35 citations · 95 across the 11 of their papers we have counts for
11 papers
Designing Algorithms for Entropic Optimal Transport from an Optimisation Perspective
Vishwak Srinivasan, Qijia Jiang
In this work, we develop a collection of novel methods for the entropic-regularised optimal transport problem, which are inspired by existing mirror descent interpretations of the…
Machine-Learned Sampling of Conditioned Path Measures
Qijia Jiang, Reuben Cohn-Gordon
We propose algorithms for sampling from posterior path measures under a general prior process. This leverages ideas from (1) controlled equilibrium dyn…
Control, Transport and Sampling: Towards Better Loss Design
Qijia Jiang, David Nabergoj
Leveraging connections between diffusion-based sampling, optimal transport, and stochastic optimal control through their shared links to the Schrödinger bridge problem, we propose…
From Estimation to Sampling for Bayesian Linear Regression with Spike-and-Slab Prior
Qijia Jiang
We consider Bayesian linear regression with sparsity-inducing prior and design efficient sampling algorithms leveraging posterior contraction properties. A quasi-likelihood with Ga…
On the Dissipation of Ideal Hamiltonian Monte Carlo Sampler
Qijia Jiang
We report on what seems to be an intriguing connection between variable integration time and partial velocity refreshment of Ideal Hamiltonian Monte Carlo samplers, both of which c…
Learning the Truth From Only One Side of the Story
Heinrich Jiang, Qijia Jiang, Aldo Pacchiano
Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications incl…
Acceleration with a Ball Optimization Oracle
Yair Carmon, Arun Jambulapati, Qijia Jiang +4
Consider an oracle which takes a point and returns the minimizer of a convex function in an ball of radius around . It is straightforward to show that rough…
Optimizing Black-box Metrics with Adaptive Surrogates
Qijia Jiang, Olaoluwa Adigun, Harikrishna Narasimhan +2
We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surroga…
Complexity of Highly Parallel Non-Smooth Convex Optimization
Sébastien Bubeck, Qijia Jiang, Yin Tat Lee +2
A landmark result of non-smooth convex optimization is that gradient descent is an optimal algorithm whenever the number of computed gradients is smaller than the dimension . In…
Near-optimal method for highly smooth convex optimization
Sébastien Bubeck, Qijia Jiang, Yin Tat Lee +2
We propose a near-optimal method for highly smooth convex optimization. More precisely, in the oracle model where one obtains the order Taylor expansion of a function at t…
Subgradient Descent Learns Orthogonal Dictionaries
Yu Bai, Qijia Jiang, Ju Sun
This paper concerns dictionary learning, i.e., sparse coding, a fundamental representation learning problem. We show that a subgradient descent algorithm, with random initializatio…