Find Events

September 2018

## Topics in Information and Inference Seminar

September 20, 2018 @ 4:00 pm - 5:00 pm

Yury Polyanskiy (MIT )

32-D677

Title: Strong data processing inequalities and information percolation Abstract: The data-processing inequality, that is, $I(U;Y) \le I(U;X)$ for a Markov chain $U \to X \to Y$, has been the method of choice for proving impossibility (converse) results in information theory and many other disciplines. A channel-dependent improvement is called the strong data-processing inequality (or SDPI). In this talk we will: a) review SDPIs; b) show how point-to-point SDPIs can be combined into an SDPI for a network; c) show recent…

Find out more »
August 2018

## Resource-efficient ML in 2 KB RAM for the Internet of Things

August 21, 2018 @ 2:00 pm - 3:00 pm

Prateek Jain (Microsoft Research)

E18-304

Abstract: We propose an alternative paradigm for the Internet of Things (IoT) where machine learning algorithms run locally on severely resource-constrained edge and endpoint devices without necessarily needing cloud connectivity. This enables many scenarios beyond the pale of the traditional paradigm including low-latency brain implants, precision agriculture on disconnected farms, privacy-preserving smart spectacles, etc. Towards this end, we develop novel tree and kNN based algorithm, called Bonsai and ProtoNN, for efficient prediction on IoT devices — such as those based…

Find out more »
February 2018

## Provably Secure Machine Learning

February 26, 2018 @ 4:00 pm - 5:00 pm

Jacob Steinhardt (Stanford)

32-G449 (Kiva/Patel)

Abstract:  The widespread use of machine learning systems creates a new class of computer security vulnerabilities where, rather than attacking the integrity of the software itself, malicious actors exploit the statistical nature of the learning algorithms. For instance, attackers can add fake data (e.g. by creating fake user accounts), or strategically manipulate inputs to the system once it is deployed. So far, attempts to defend against these attacks have focused on empirical performance against known sets of attacks. I will argue that…

Find out more »

© MIT Institute for Data, Systems, and Society | 77 Massachusetts Avenue | Cambridge, MA 02139-4307 | 617-253-1764 | Design by Opus