Zheng Qu — accepted AI-conference papers

2021

Coordinated Motion Generation and Object Placement: A Reactive Planning and Landing Approach

Riddhiman Laha, Jonathan Vorndamme, Luis F.C. Figueredo, Zheng Qu, Abdalla Swikir, Christoph Jähne +1

IROS 2021poster

Similar to human work, robotic tasks sometimes require two hands to be accomplished. This requires coordinated motion planning and control. While fulfilling the task in a coordinated manner is already a big challenge, the task at hand becomes even harder when obstacles are introduced in the environm…

Cited by 13 Source ↗Scholar ↗

2021

Introducing GARMI - A Service Robotics Platform to Support the Elderly at Home: Design Philosophy, System Overview and First Results

Mario Tröbinger, Christoph Jähne, Zheng Qu, Jean Elsner, Anton Reindl, Sebastian Getz +11

RA-L 2021

This letter introduces GARMI, a service robotics platform conceptualized with a focus on assisting elderly at home. GARMI is designed to provide support with household tasks, as an avatar for tactile-enabled communication and as an interface for telemedicine and emergency assistance. Its unique huma

Cited by 78 Source ↗Scholar ↗

2019

SAGA with Arbitrary Sampling

Xun Qian, Zheng Qu, Peter Richtárik

ICML 2019oral

We study the problem of minimizing the average of a very large number of smooth functions, which is of key importance in training supervised learning models. One of the most celebrated methods in this context is the SAGA algorithm of Defazio et al. (2014). Despite years of research on the topic, a g…

Cited by 28 Source ↗PDF ↗Scholar ↗

2016

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling

Zeyuan Allen-Zhu, Zheng Qu, Peter Richtarik, Yang Yuan

ICML 2016poster

Accelerated coordinate descent is widely used in optimization due to its cheap per-iteration cost and scalability to large-scale problems. Up to a primal-dual transformation, it is also the same as accelerated stochastic gradient descent that is one of the central methods used in machine learning. I…

Cited by 217 Source ↗PDF ↗Scholar ↗

2016

SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization

Zheng Qu, Peter Richtarik, Martin Takac, Olivier Fercoq

ICML 2016poster

We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subset of the dual variables. However, unlike existing methods such as stochastic dual coordinate ascent, SDNA is capable of…

Cited by 115 Source ↗PDF ↗Scholar ↗

2015

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling

Zheng Qu, Peter Richtarik, Tong Zhang

NeurIPS 2015poster

We study the problem of minimizing the average of a large number of smooth convex functions penalized with a strongly convex regularizer. We propose and analyze a novel primal-dual method (Quartz) which at every iteration samples and updates a random subset of the dual variables, chosen according to…

Cited by 144 Source ↗PDF ↗Scholar ↗

2015

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

Dominik Csiba, Zheng Qu, Peter Richtarik

ICML 2015poster

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method adaptively change the probability distribution over the dual variables throughout the iter…

Cited by 107 Source ↗PDF ↗Scholar ↗