News & EventsDepartment Events & Announcements
Events
-
Oct15
EVENT DETAILS
less
Wednesday / CS Seminar
October 15th / 12:00 PM
Hybrid / Mudd 3514Speaker
Jason Hartline, Northwestern UniversityTalk Title
Scoring Rules for a Theory of AIAbstract
Scoring rules are foundational in decision theory and, therefore, are foundational for a developing theory of artificial intelligence. Just as simple models from decision theory provide context for understanding the decisions of complex humans, so too can they for complex AI systems. Bayesian decision theory considers an agent receiving a signal that is correlated with the state, choosing an action, and obtaining a payoff that depends on both the state and action. With Bayesian updating and the revelation principle, the signal becomes a posterior belief and the decision problem becomes a scoring rule. Given a scoring rule, baseline performance is the optimal score under the prior; benchmark performance is the optimal score under the posterior; and the optimal scoring rule — framed as a mechanism design problem — maximizes the difference between them. The talk reviews this theory and applies it to evaluate the value of information, the losses from predictive models, and the accuracy of human and AI decision makers.Biography
"Prof. Hartline’s research introduces design and analysis methodologies from computer science to understand and improve outcomes of economic, legal, and AI systems. Optimal behavior and outcomes in complex environments are complex and, therefore, should not be expected; instead, the theory of approximation can show that simple and natural behaviors are approximately optimal in complex environments. This approach is applied to auction theory and mechanism design in his graduate textbook Mechanism Design and Approximation which is under preparation.
Prof. Hartline received his Ph.D. in 2003 from the University of Washington under the supervision of Anna Karlin. He was a postdoctoral fellow at Carnegie Mellon University under the supervision of Avrim Blum; and subsequently a researcher at Microsoft Research in Silicon Valley. He joined Northwestern University in 2008 where he is a professor of computer science. He was on sabbatical at Harvard University in the Economics Department during the 2014 calendar year and visiting Microsoft Research, New England for the Spring of 2015. He was on sabbatical at Stanford University for the 2023-2024 academic year.
Prof. Hartline is the director of Northwestern’s Online Markets Lab, he was a founding codirector of the Institute for Data, Econometrics, Algorithms, and Learning from 2019-2022, and is a cofounder of virtual conference organizing platform Virtual Chair."
TIME Wednesday, October 15, 2025 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Aug17
EVENT DETAILS
lessThis dissertation investigates the use of large language models (LLMs) as variation operators for evolving programs. Whereas a traditional variation operator modifies program syntax without regard to program behavior, an LLM can propose changes informed by the semantics of the code. This capability has enabled new forms of program evolution and produced promising results, yet the behavior of LLM-based evolutionary operators remains comparatively understudied. This dissertation examines three forces that shape the resulting evolutionary process: the representation of candidate programs, the method of selection that determines which candidates persist across generations, and the dynamics of the variation operator itself. Each of these factors influences the capacity for sustained, open-ended exploration.
To study representation, we evolved agent rules for multi-agent simulations implemented in NetLogo and introduced three benchmark environments for evaluating LLM-generated code in this setting. Three ways of representing the same rule were compared: executable code, code with comments, and pseudocode that a separate model call converts into executable code. Across all three environments, evolving commented code produced the highest-performing agents, while evolving pseudocode produced the lowest-performing agents, indicating that natural language aids the variation operator when it augments executable code rather than replacing it.
To study selection, we varied the balance between objective performance and behavioral novelty while evolving agent rules. Final fitness was largely unaffected by this balance, but greater emphasis on novelty consistently yielded a higher proportion of qualitatively superior code structures. These findings suggest that diversity-driven search can improve the quality of evolved code, revealing a hidden cost of objective-centric optimization.
To study the operator itself, we asked whether a language model that repeatedly mutates a program continues to explore new forms or instead returns to recurring structures. Mutation chains were analyzed in the absence of selection pressure within a domain-specific language, varying prompt design, model family, and stochastic replication. The chains converged on restricted regions of program space, with most variation confined to substitutions within recurring structural templates, while a classical genetic programming mutation operator showed no comparable convergence under matched conditions.
These three forces do not act independently. The representation determines the extent to which the capabilities of the variation operator can be exploited, selection determines which resulting programs persist and become available for further variation, and the dynamics of the operator shape the structures that repeated mutation continues to produce. LLM-driven program evolution can effectively evolve agent rules for multi-agent systems, but its outcomes are sensitive to design choices that are easily left implicit. The selection regime changes the quality of the program structures that survive, while the same semantic capabilities that allow an LLM to transform programs can also introduce a systematic bias toward structural homogeneity. Whether these systems can sustain open-ended exploration depends on the interaction among representation, selection, and variation.TIME Monday, August 17, 2026 at 10:00 AM - 12:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Jensen Smith jensen.smith@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Aug20
EVENT DETAILS
lessThe component-by-component migration of a program from untyped to typed can trigger unintended performance degradations. When such a degradation occurs, typing well-chosen components can lessen the cost of type enforcement, while typing poorly chosen components can exacerbate it. In this talk, I examine whether off-the-shelf profiling tools deliver information that helps programmers navigate these migration choices effectively in Typed Racket.
TIME Thursday, August 20, 2026 at 1:00 PM - 4:00 PM
LOCATION Mudd 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Jensen Smith jensen.smith@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Sep14
EVENT DETAILS
lessEnjoy a welcome from Dean Christopher A. Schuh and other McCormick leaders, and receive a Northwestern Engineering T-shirt. A free breakfast on the Tech East Plaza will follow.
TIME Monday, September 14, 2026 at 9:00 AM - 10:30 AM
LOCATION LR2, Technological Institute map it
CONTACT Andi Joppie andi.joppie@northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science
-
Sep22
EVENT DETAILS
lessEnjoy a welcome from Dean Christopher A. Schuh and other McCormick leaders, and receive a Northwestern Engineering T-shirt. A free lunch on the Tech East Plaza will follow.
TIME Tuesday, September 22, 2026 at 11:00 AM - 12:30 PM
LOCATION Ryan Family Auditorium, Technological Institute map it
CONTACT Andi Joppie andi.joppie@northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science
-
Sep24
EVENT DETAILS
lesstba
TIME Thursday, September 24, 2026 at 9:00 AM - 11:00 AM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Sep28
EVENT DETAILS
lessMonday / CS Seminar
September 28 / 12:00 PM
Hybrid / Mudd 3514Speaker
TBATalk Title
TBAAbstract
TBABiography
TBA---
Zoom Link
Panopto LinkTIME Monday, September 28, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Oct5
EVENT DETAILS
lessMonday / CS Seminar
October 5 / 12:00 PM
Hybrid / Mudd 3514Speaker
Brian Suchy, Software Engineer Google DeepMindTalk Title
Formal Relational Equivalence for SQL, GenAI, and BeyondAbstract
Verifying that complex query rewrites from database optimizers or AI-driven generators preserve exact bag semantics under three-valued logic is an NP-hard challenge. To address this, we present an MLIR-native compiler framework that formally reasons about relational algebra. By decoupling query semantics from specific execution engines and lowering queries into a unified Relational Algebra Intermediate Representation, our language-agnostic methodology definitively proves semantic equivalence across all possible database states.The core of the presentation will deep-dive into our multi-tiered proving architecture, which synthesizes several advanced academic methodologies. First, we utilize E-Graphs and Equality Saturation to rapidly explore the equivalence space and detect structural congruence between query abstract syntax trees using fast, algebraic rewrite rules. Second, we employ Semiring Arithmetic, treating relational algebra as expressions over K-relations to leverage algebraic simplification and canonical forms under semiring laws. Finally, we implement a First-Order Logic and SMT translation path, lowering Relational Algebra into Relational Calculus and then into First-Order Logic to evaluate constraints and domain-specific axioms using parallel solvers like Z3 and CVC5, which either formally proves equivalence or synthesizes concrete counter-examples.
Finally, we will discuss the practical implications of combining these formal mathematical methods with modern compiler design. Attendees will leave with a comprehensive understanding of how bridging database theory, equality saturation, and SMT solving can create robust solutions for verifying query optimizers, enforcing semantic correctness, and validating automated SQL generation at scale.
Biography
Brian Suchy is a Software Engineer within Google DeepMind.
In his time at Google he has worked on F1 Query (Google's internal SQL query engine), hardware development, and (of course) AI.
Prior to joining Google, Brian received his PhD student at Northwestern University, advised by Peter Dinda, with a focus on hardware/software codesign and memory management.Research Interests: Artificial Intelligence, Query Processing and Formal Logic
---
Zoom Link
Panopto LinkTIME Monday, October 5, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Oct29
EVENT DETAILS
lesstba
TIME Thursday, October 29, 2026 at 9:00 AM - 11:00 AM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Nov19
EVENT DETAILS
lesstba
TIME Thursday, November 19, 2026 at 9:00 AM - 11:00 AM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)