Winter term ends

Xue will describe a line of work on designing robust algorithms with provable guarantees for learning signals that have sparse representations in the Fourier domain.

Longfei will present two examples of his research on pushing the limits of wireless connectivity for IoT devices.

Shagufta will present how to effectively detect crypto-ransomware and insider cyber attacks at an early stage by using machine learning techniques as one of the key components.

Qing will present global nonconvex optimization theory and guaranteed algorithms for efficient learning of low-complexity models from high-dimensional data.

In this talk, Hong will present two works that explore the program data space to provide comprehensive protections and to find new devastating attacks.

Shiyu will talk about how rationales are established to improve model interpretability. After that, he will discuss how human-generated rationales impact learning performance.

In this talk, Hasti will present her research in supporting three groups of future haptics creators: 1) end users, 2) interaction designers, and 3) haptics experts.

Wei will share his experience on detecting and mitigating web attacks and abuses through dynamic program monitoring.

In this talk, Han will discuss his recent work on understanding and learning invariant representations.