Preprints:
Graph cuts always find a global optimum for Potts models (with a catch) (in submission).
HL, D. Sontag, A. Vijayaraghavan.
Statistical adaptive stochastic gradient methods.
P. Zhang, HL, Q. Liu, L. Xiao.
Publications:
Beyond perturbation stability: LP recovery guarantees for MAP inference on noisy stable instances (AISTATS 2021).
HL*, A. Reddy*, D. Sontag, A. Vijayaraghavan.
*equal contribution
Self-supervised self-supervision by combining deep learning and probabilistic logic (AAAI 2021).
HL, H. Poon.
Using statistics to automate stochastic optimization (NeurIPS 2019).
HL, P. Zhang, L. Xiao.
Understanding the role of momentum in stochastic gradient methods (NeurIPS 2019).
I. Gitman, HL, P. Zhang, L. Xiao.
Block stability for MAP inference (AISTATS 2019, oral presentation).
HL, D. Sontag, A. Vijayaraghavan.
Optimality of
approximate inference algorithms on stable instances (AISTATS
2018).
HL, D. Sontag, A. Vijayaraghavan.