Penn Engineering Events

CIS

  1. Events
  2. CIS

Events Search and Views Navigation

Event Views Navigation

Today

ASSET Seminar: New approaches to detecting and adapting to domain shifts in machine learning, Zico Kolter, Ph.D. (Carnegie Mellon University)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT: Machine learning systems, in virtually every deployed system, encounter data from a qualitatively different distribution than what they were trained upon.  Effectively dealing with this problem, known as domain shift, is thus perhaps the key challenge in deploying machine learning methods in practice.  In this talk, I will motivate some of these challenges in […]

CIS Seminar: “Rater Equivalence: An Interpretable Measure of Classifier Accuracy Against Human Labels”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

In many classification tasks, the ground truth is either noisy or subjective. Examples of noisy ground truth include: does this radiology image show a cancerous growth? does this radar data portend an imminent tornado? Examples of subjective ground truth include: which of two alternative paper titles is better? is this comment toxic? what is the […]

CIS Seminar: “The Long Arm of Theoretical Computer Science: A Case Study in Blockchains/Web3”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Blockchains that support a general contract layer (e.g., Ethereum) export the functionality of a general-purpose, ownerless, and open-access computer that can enforce property rights for digital data.  How is such functionality implemented?  Using a lot of extremely cool computer science ideas! And like everywhere else in computer science, theory plays an undeniable role in the […]

ASSET Seminar: How to Design Molecules that Dock Well but Can’t Exist, Jacob Gardner, Ph.D.

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT:BIO Machine learning has become an indispensable aid to researchers developing the next generation of novel therapeutics. In this talk, I will discuss how some of the most important problems  in virtual screening for new potential drug molecules can be cast as black-box optimization problems, where the goal is to find molecules maximizing some desired property […]

CIS Seminar: “Designing Hardware for Cryptography and Cryptography for Hardware”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

There have been few high-impact deployments of hardware implementations of cryptographic primitives. We present the benefits and challenges of hardware acceleration of sophisticated cryptographic primitives and protocols, and describe our recent design work in accelerating Fully Homomorphic Encryption by three to four orders of magnitude using programmable hardware accelerators. We argue the significant potential for […]

CIS Seminar: “Designing Hardware for Cryptography and Cryptography for Hardware”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

There have been few high-impact deployments of hardware implementations of cryptographic primitives. We present the benefits and challenges of hardware acceleration of sophisticated cryptographic primitives and protocols, and describe our recent design work in accelerating Fully Homomorphic Encryption by three to four orders of magnitude using programmable hardware accelerators. We argue the significant potential for […]

ASSET Seminar: Building certifiably safe and correct large-scale autonomy, Chuchu Fan (Massachusetts Institute of Technology)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT: The introduction of machine learning (ML) and artificial intelligence (AI) creates unprecedented opportunities for achieving full autonomy. However, learning-based methods in building autonomous systems can be extremely brittle in practice and are not designed to be verifiable. In this talk, I will present several of our recent efforts that combine ML with formal methods […]

ASSET Seminar: Decision-Aware Learning for Global Health Supply Chains, Osbert Bastani (University of Pennsylvania)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT: Machine learning algorithms are increasingly used in conjunction with optimization to guide decision making. A key challenge is aligning the machine learning loss with the decision-making loss. Existing solutions have limited flexibility and/or scale poorly to large datasets. We propose a principled decision-aware learning algorithm that uses a Taylor expansion of the optimal decision […]

CIS Seminar: “Generative multitask learning mitigates target-causing confounding”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

We propose a simple and scalable approach to causal representation learning for multitask learning. Our approach requires minimal modification to existing ML systems, and improves robustness to prior probability shift. The improvement comes from mitigating unobserved confounders that cause the targets, but not the input. We refer to them as target-causing confounders. These confounders induce […]