Microsoft at NeurIPS 2020
Location: Virtual
Microsoft Research blog
Denoised smoothing: Provably defending pretrained classifiers against adversarial examples
| Hadi Salman
Editor’s note: This post and its research are the result of the collaborative efforts of a team of researchers comprising former Microsoft Research Engineer Hadi Salman (opens in new tab), CMU PhD student Mingjie Sun (opens in new tab), Researcher…
‘Seeing’ on tiny battery-powered microcontrollers with RNNPool
| Oindrila Saha, Shikhar Jaiswal, Aayan Kumar, Harsha Simhadri, and Prateek Jain
Computer vision has rapidly evolved over the past decade, allowing for such applications as Seeing AI (opens in new tab), a camera app that describes aloud a person’s surroundings, helping those who are blind or have low vision; systems that…
MPNet combines strengths of masked and permuted language modeling for language understanding
| Xu Tan
Pretrained language models have been a hot research topic in natural language processing. These models, such as BERT, are usually pretrained on large-scale language corpora with carefully designed pretraining objectives and then fine-tuned on downstream tasks to boost the accuracy.…
NeurIPS 2020: Moving toward real-world reinforcement learning via batch RL, strategic exploration, and representation learning
As human beings, we encounter unfamiliar situations all the time—learning to drive, living on our own for the first time, starting a new job. And while we can anticipate what to expect based on what others have told us or…
Utilizing consumer cameras for contact-free physiological measurement in telehealth and beyond
| Daniel McDuff and Xin Liu
According to the CDC WONDER Online Database (opens in new tab), heart disease is currently the leading cause of death for both men and women in the United States. However, most deaths due to cardiovascular diseases could be prevented with…
A Microsoft custom data type for efficient inference
| Bita Darvish Rouhani, Doug Burger, Eric Chung, Rangan Majumder, Sangeetha Shekar, Saurabh Tiwary, Sitaram Lanka, and Steve Reinhardt
AI is taking on an increasingly important role in many Microsoft products, such as Bing and Office 365. In some cases, it’s being used to power outward-facing features like semantic search in Microsoft Word or intelligent answers in Bing, and…
Adversarial machine learning and instrumental variables for flexible causal modeling
| Vasilis Syrgkanis
We are going through a new shift in machine learning (ML), where ML models are increasingly being used to automate decision-making in a multitude of domains: what personalized treatment should be administered to a patient, what discount should be offered…
Adversarial robustness as a prior for better transfer learning
| Hadi Salman
Editor’s note: This post and its research are the collaborative efforts of our team, which includes Andrew Ilyas (PhD Student, MIT), Logan Engstrom (PhD Student, MIT), Aleksander Mądry (Professor at MIT), Ashish Kapoor (Partner Research Manager). In practical machine learning,…