We give an algorithm that computes exact maximum flows and minimum-cost flows on
directed graphs with m edges and polynomially bounded integral demands, costs, and …

Autoregressive sampling from large language models has led to state-of-the-art results in
several natural language tasks. However, autoregressive sampling generates tokens one at …

The success of deep learning is largely attributed to the training over clean data. However,
data is often coupled with noisy labels in practice. Learning with noisy labels is challenging …

We present a new behavioural distance over the state space of a Markov decision process,
and demonstrate the use of this distance as an effective means of shaping the learnt …

We provide a computational complexity analysis for the Sinkhorn algorithm that solves the
entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures …

This paper discusses the efficiency of Hybrid Primal-Dual (HPD) type algorithms to
approximately solve discrete Optimal Transport (OT) and Wasserstein Barycenter (WB) …

Optimal transport is an important tool in machine learning, allowing to capture geometric
properties of the data through a linear program on transport polytopes. We present a single …

Sinkhorn algorithm has been used pervasively to approximate the solution to optimal
transport (OT) and unbalanced optimal transport (UOT) problems. However, its practical …

Distribution comparison plays a central role in many machine learning tasks like data
classification and generative modeling. In this study, we propose a novel metric, called …

We present several new complexity results for the entropic regularized algorithms that
approximately solve the optimal transport (OT) problem between two discrete probability …