Description:

Monday / CS Seminar
January 13th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Xiaotian Zhang, University of Illinois at Urbana-Champaign

Talk Title
Decoding neuro-mechanical intelligence for novel machines and biological discovery

Abstract
Natural creatures, from worms and snakes to fishes and octopuses, possess remarkable mobility and dexterity, often unmatched by engineering counterparts. Central to their abilities is the intimate meshing between mechanical and neural infrastructures, whereby each enhances and supports the other across scales. To decode the key principles at play and streamline their use in engineering, I will present a multidisciplinary approach based on a unique blend of numerical and experimental techniques. First, I will introduce a computational framework for investigating the dynamics and embodied control principles of complex musculoskeletal architectures. I will then demonstrate the extended utility of this framework in designing and realizing living robots. Finally, I will present a set of technologies aimed at decoding neural dynamics for computation and robotics. Together, these techniques promise a novel class of engineering system that exploits neuro-mechanical convergence for intelligent behaviors.

Biography
Xiaotian Zhang is a postdoctoral research associate at the Carl R. Woese Institute for Genomic Biology at the University of Illinois at Urbana-Champaign, where he also earned his Ph.D. in Mechanical Engineering under the mentorship of Prof. Mattia Gazzola. His research focuses on understanding biological principles to inspire novel system design and control, through the synergy of biophysical simulation, neural engineering, and robotics. His work has been featured in high-profile interdisciplinary journals and highlighted through several cover images.

Research/Interest Areas
Soft mechanics, Neural engineering, Robotics
---
Zoom: https://northwestern.zoom.us/j/98147065932?pwd=y27zLmqlr1NnFrVq3sbwmlolZPdKEB.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=60759d9c-5a7a-452b-8e73-b25f01539f31 
DEI Minute: tinyurl.com/cspac-dei-minute

Description:

Wednesday / CS Seminar
January 15th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Sainyam Galhotra, Cornell University

Talk Title
Context-aware Responsible Data Science

Abstract
"Data-based systems are increasingly used in applications that have far-reaching consequences and long-lasting societal impact. However, the development process remains highly specialized, tedious, and unscalable. This produces a manually fine-tuned rigid solution that works only for one specific problem in one specific context. The system fails to adapt to the changing world and severely limits the full utilization of valuable data.

So, how can you avert this fate for your systems?

In this talk, I present my vision of context-aware systems that enable even non-expert users to develop correct, explainable, and equitable data-science pipelines. To achieve this, I will focus on i) re-thinking the design of data science pipelines, and ii) the importance of causal inference for trustworthy data analysis. I will present a data discovery framework that automatically identifies useful data on behalf of end-users for various tasks. Lastly, I will discuss my proposal of leveraging counterfactual reasoning and causal inference to quantify the impact of an input on the outcome. These topics are the pieces of the puzzle that come together to create the Data Scientists' holy grail - an easily deployable, scalable, and robust system that you can trust even as everything around it evolves."

Biography
Sainyam Galhotra is an Assistant Professor in Computer Science at Cornell University and a field member for Computer Science, Statistics and Data Science. Previously, he was a Computing Innovation Fellow pursuing postdoctoral research at the University of Chicago. He received his Ph.D. from the University of Massachusetts Amherst under the supervision of Prof. Barna Saha (currently at UC San Diego). The goal of his research is to lay the foundation of responsible data science, that enable efficient development and deployment of trustworthy data analytics applications. His research has combined techniques from Data Management, Probabilistic Methods, Causal Inference, Machine Learning, and Software Engineering. His research has been published in top-tier Data Management (SIGMOD, VLDB, PODS, & ICDE), AI (NeurIPS, AAAI & AIES) and Software Engineering (FSE) conferences. He is a recipient of the Best Paper Award in FSE 2017 and Most Reproducible Paper Award in both SIGMOD 2017 and 2018, and Best Artifact Paper Honorable Mention Award in SIGMOD 2023. He was recognized as a Data Science rising star, a DAAD AInet Fellow, and as the first recipient of the Krithi Ramamritham Award at UMass for contribution to database research.

Research/Interest Areas
Data Management
---
Zoom: https://northwestern.zoom.us/j/92345079181?pwd=4K3AzzUtPHxoMnaB97EZqRXJ5s4vva.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=07420843-9285-40df-81c0-b26001574825
DEI Minute: Diversity tinyurl.com/cspac-dei-minute

Description:

Wednesday / CS Seminar
January 22nd / 12:00 PM
Hybrid / Mudd 3514

Speaker
Ankit Garg, Microsoft Research India

Talk Title
Arithmetic circuits: lower bounds, learning and applications

Abstract
Arithmetic circuits are a natural model for computing polynomials via the basic operations of addition and multiplication. One of the fundamental open problems in this area is of proving lower bounds, i.e. finding an explicit polynomial that cannot be computed by polynomial sized arithmetic circuits (aka the VP vs VNP problem). While the question of proving lower bounds for general arithmetic circuits is still open, there has been remarkable progress in proving lower bounds for restricted classes of arithmetic circuits. Another important problem in this area is that of learning arithmetic circuits: given a polynomial (via query or black box access), output a small arithmetic circuit computing it (if one exists). This problem is hard in the worst case. I will present a meta framework for learning arithmetic circuits in the non-degenerate case using lower bound methods. We instantiate and implement this meta framework for various classes of arithmetic circuits. Then I will talk about extending the algorithms to the noisy setting as well as surprising and remarkable applications to classical problems in machine learning such as subspace clustering and mixtures of Gaussians. This is based on joint works with Pritam Chandra, Neeraj Kayal, Kunal Mittal, Chandan Saha and Tanmay Sinha.

Biography
Ankit Garg is a Senior Researcher at Microsoft Research India since July 2018. Prior to this, he was a Postdoctoral Researcher at Microsoft Research New England from 2016 - 2018. He completed his PhD in 2016 from Princeton University under the supervision of Prof Mark Braverman. His research has spanned several areas of theoretical computer science such as communication complexity, arithmetic complexity, optimization, mixture models and optimization. Several of his research papers have been published in top conferences in computer science such as STOC, FOCS, CCC, NeuRIPS and QIP, and recognized by Simons award for graduate students in theoretical computer science and a Siebel scholarship.

Research/Interest Areas
Theoretical Computer Science, Algorithms, Computational Complexity Theory

---
Zoom: https://northwestern.zoom.us/j/92525649422?pwd=N6DlLBx6RRAtrar8vk27te6cjmzqXP.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=4d9fd60c-89e5-48f6-bbdb-b261015638de
DEI Minute: tinyurl.com/cspac-dei-minute

Description:

Friday / CS Seminar
January 24th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Meena Jagadeesan, UC Berkeley

Talk Title
Steering Machine Learning Ecosystems of Interacting Agents

Abstract

"Modern machine learning models—such as LLMs and recommender systems—interact with humans, companies, and other models in a broader ecosystem. However, these multi-agent interactions often induce unintended ecosystem-level outcomes such as clickbait in classical content recommendation ecosystems, and more recently, safety violations and market concentration in nascent LLM ecosystems. 

In this talk, I discuss my research on characterizing and steering ecosystem-level outcomes. I take an economic and statistical perspective on ML ecosystems, tracing outcomes back to the incentives of interacting agents and to the ML pipeline for training models. First, in LLM ecosystems, we show how analyzing a single model in isolation fails to capture ecosystem-level performance trends: for example, training a model with more resources can counterintuitively hurt ecosystem-level performance. To help steer ecosystem-level outcomes, we develop technical tools to assess how proposed policy interventions affect market entry, safety compliance, and user welfare. Then, turning to content recommendation ecosystems, we characterize a feedback loop between the recommender system and content creators, which shapes the diversity and quality of the content supply. Finally, I present a broader vision of ML ecosystems where multi-agent interactions are steered towards the desired algorithmic, market, and societal outcomes."

Biography
Meena Jagadeesan is a 5th year PhD student in Computer Science at UC Berkeley, where she is advised by Michael I. Jordan and Jacob Steinhardt. Her research investigates multi-agent interactions in machine learning ecosystems from an economic and statistical perspective. She has received an Open Philanthropy AI Fellowship and a Paul and Daisy Soros Fellowship.

Research/Interest Areas
Artificial Intelligence, Machine Learning, Economics and Computation
---
Zoom: https://northwestern.zoom.us/j/92665903240?pwd=YGOjSzB0Pxk4oDvRsVBbA0auFIvH0p.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=408ccd84-8bf4-409a-b995-b261015654c8
DEI Minute: tinyurl.com/cspac-dei-minute

Description:

Monday / CS Seminar
January 13th / 12:00 PM
Hybrid / Mudd 3514

Speaker
TBA

Talk Title
TBA

Abstract
TBA

Biography
TBA

Research/Interest Areas
TBA
---
Zoom: TBA
Panopto: TBA
DEI Minute: tinyurl.com/cspac-dei-minute