Spring Seminar Series – Dr. Hongseok Namkoong

A New Computation-driven Framework for Adaptive Experimentation

Hongseok Namkoong, PhD

Assistant Professor in the Decision, Risk, and Operations division

Columbia Business School

4/21/2023

11 am – 12pm CST

WebEx: https://utsa.webex.com/utsa/j.php?MTID=m568fe3d73989cb26d676f896e952c3c0

Abstract:  Experimentation serves as the foundation of scientific decision-making. Adaptive allocation of measurement effort can significantly improve statistical power. However, implementing standard bandit algorithms, which assume continual reallocation of measurement effort, is challenging due to delayed feedback and infrastructural or organizational difficulties. To address this, we introduce a new framework for adaptive experimentation, motivated by practical instances involving a limited number of reallocation epochs in which outcomes are measured in batches. Our framework diverges from the traditional theory-driven paradigm by utilizing computational tools for algorithmic design.

We observe that normal approximations, which are universal in statistical inference, can also guide the design of scalable adaptive designs. By deriving an asymptotic sequential experiment, we formulate a dynamic program that can leverage prior information on average rewards. We propose a simple iterative planning method called Residual Horizon Optimization, which selects sampling allocations by optimizing a planning objective. Our method significantly improves statistical power over standard adaptive policies, even when compared to Bayesian bandit algorithms (e.g., Thompson sampling) that require full distributional knowledge of individual rewards. Overall, we expand the scope of adaptive experimentation to settings that pose difficulties for standard adaptive policies, including problems with a small number of reallocation epochs, low signal-to-noise ratio, and unknown reward distributions.

This work was led by Ethan Che. Paper link: https://arxiv.org/abs/2303.11582.

2023 Neuro-Inspired Computing Elements (NICE) Conference

Dates: 11 – 14 April 2023

• NICE workshop: Tuesday, 11 April – Thursday, 13 April 2023
  
• NICE hands-on tutorials day: Friday, 14 April 2023

Venue

On site attendance at the University of Texas in San Antonio (UTSA.edu) (pending any COVID related changes).

Focus

The 2023 Neuro-Inspired Computing Elements (NICE) Conference is the 10th annual meeting of researchers in the neural computing field. Like previous editions, NICE 2023 will focus on the interplay between neural theory, neural algorithms, neuromorphic architectures and hardware, and applications for neural computing technology.

NICE aims to involve diverse participation from all over the world and bring together research communities with universities, government, and industry.

Call for papers – open until 11 December 2022

The submission of 4-8 pages papers is open HERE at easychair.

Papers should cover unpublished work and emphasize the novel aspects and the potential impact on the neural computing community. Preference will be given towards submissions describing ambitious approaches to bringing neural inspiration into real-world computing applications. From these submissions we will invite several short talks, lightning talks, and poster presentations.

We also welcome Abstracts (1-2 pages) for ‘Work in Progress’ or ‘Late Breaking News’. These submissions will be considered for poster presentations, lightning talks or demonstrations when applicable. These submissions will not be considered for the proceedings.

As with previous years, NICE is planning on publishing an online proceedings volume, details are below. Authors can also opt out of including their paper in the proceedings.

Submission deadline	December 11, 2022
Notification of Acceptance	February 1, 2023
Camera-ready Submission	February 27, 2023

List of Topics

Listed below are the topics for the conference, together with a non-exhaustive list of relevant sub-topics.

• Architectures and Hardware 
  • Neuromorphic Hardware
  • Analog/Mixed-Signal and Beyond-CMOS Hardware
  • Compute-In-Memory Architectures
  • Next-Generation Architectures
• Computational and Systems Neuroscience
  • Neural circuits: Theory and Experimental Support
  • Local learning and Plasticity
  • Connectomics
• Neural Algorithms and Machine Learning
  • Neuroscience-Inspired Algorithms
  • Resource-Constrained and/or Hardware-Aware Artificial Neural Networks
  • Spiking Neural Networks
• Neuromorphic Computing Applications
  • Emerging Applications
  • Robotics and Automation
  • High-Performance Computing
  • Edge Computing
  • Biosignal Processing and Brain-Computer Interfaces
• Bio-Inspired Sensing
  • Event-Driven Sensing
  • Novel Neuromorphic Sensors
  • Efficient Spike-Based Information Coding and Processing
• Algorithms and Software Frameworks for Neuromorphic Computing
  • Tools and Programming/Mapping Frameworks
  • Benchmarks, Neuromorphic Datasets
  • Theoretical Frameworks and Models for Neuromorphic Engineering
  • Memory-efficient Spike-Based Simulators

Tutorials

Tutorials will be offered on Friday, 14 April 2023.

Please contact Dr. Brad Aimone (jbaimon@sandia.gov) if you are interested in presenting a tutorial at the conference.

Special Seminar Series – Dr. Nancy Chen

Neural Language Generation: From Self-Supervised Representation Learning to Multimodal Contextualization

Dr. Nancy Chen

Infocomm Research (I2R), A*STAR (Agency for Science, Technology, and Research), Singapore

Wednesday, April 5, 2023

9AM – 10AM CST

WebEx: https://utsa.webex.com/utsa/j.php?MTID=m66139b13650b563509afee98c46142e9

Abstract:

The recent rapid advancements of neural language models have awed both domain experts and laymen alike. Such language models can fuel many natural language generation applications, including summarization, conversational agents, and machine translation. In this talk, we will illustrate how to harness the capabilities of these language models from a research perspective to address on-going technical challenges. In particular, we will delve into four research themes: scalable data augmentation, factually consistent generation, controllable neural modelling, and multimodal contextualization.

Spring Seminar Series – Dr. Irene Chen

Beyond Bias Audits: Bringing Equity to the Machine Learning Pipeline

Dr. Irene Chen

Microsoft Research

3/31/2023

11AM – 12PM CST

WebEx: https://utsa.webex.com/utsa/j.php?MTID=m97203d6036ae3b1f22fd0fb98da3c2d1

Advances in machine learning and the explosion of clinical data have demonstrated immense potential to fundamentally improve clinical care and deepen our understanding of human health. However, algorithms for medical interventions and scientific discovery in heterogeneous patient populations are particularly challenged by the complexities of healthcare data. Not only are clinical data noisy, missing, and irregularly sampled, but questions of equity and fairness also raise grave concerns and create additional computational challenges.

In this talk, I present two approaches for leveraging machine learning towards equitable healthcare. First, I examine how to incorporate differences in access to care into the modeling step. Using a deep generative model, we examine the task of disease phenotyping in heart failure and Parkinson’s disease. Second, I demonstrate how to address one specific health disparity through the early detection of intimate partner violence from clinical indicators. Using a time-based model with noisy labels, we can correct for biases in data measurement to learn more clinically useful subtypes and improve prediction. The talk concludes with a discussion about how to rethink the entire machine learning pipeline with an ethical lens to building algorithms that serve the entire patient population

Spring Seminar Series – Dr. Douglas Brooks

Applications of Machine Learning in Industry R&D

Dr. Douglas Brooks, PhD

Southwest Research Institute (SWRI)

3/24/2023

11AM – 12PM CST

Webex: https://utsa.webex.com/utsa/j.php?MTID=mc5ef9409265da73d5d53c136180aa35f

This discussion will highlight past and present projects, showcasing the approaches and results to solving industry focused R&D challenges. The discussion will specifically highlight the unique efforts within the R&D sector. Additionally, the discussion will include some potential future concepts and thoughts.

LINK

MATRIX Spring Seminar Series – Dr. Roberto Perdisci

IoTFinder: Efficient Large-Scale Identification of IoT Devices via Passive DNS Traffic Analysis

Roberto Perdisci

Patty and D.R. Grimes Distinguished Professor in Computer Science

Director, Institute for Cybersecurity and Privacy

School of Computing

University of Georgia

3/10/2023

11am – 12pm CST

WebEx: https://utsa.webex.com/utsa/j.php?MTID=m48256e669a2ad8e4769466e25d886773

Being able to identify and enumerate potentially vulnerable IoT devices across the Internet is important, because it allows for assessing global Internet risks and enables network operators to check the hygiene of their own networks. Towards this goal, in this talk I’ll present IoTFinder, a network-based system for efficient, large-scale passive identification of IoT devices. To develop IoTFinder, we leveraged distributed passive DNS data collection, and developed a machine learning-based system that aims to accurately identify a large variety of IoT devices based solely on their DNS traffic fingerprints. IoTFinder can efficiently detect IoT devices independently of whether they reside behind a NAT or other network middleboxes, or whether they are assigned an IPv4 or IPv6 address. We designed IoTFinder as a multi-label classifier, and evaluated its accuracy in several different settings, including DNS traffic collected at a US-based ISP hosting more than 40 million clients. The experimental results show that our approach allows for accurately and efficiently detecting many diverse IoT devices, even when they are hosted behind a NAT and their traffic is “mixed” with traffic generated by other IoT and non-IoT devices hosted in the same local network.