From awd at cs.cmu.edu Mon May 4 10:44:28 2026 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Mon, 4 May 2026 10:44:28 -0400 Subject: Fwd: RI PhD Thesis Proposal - Willa Potosnak In-Reply-To: References:

Message-ID: It is impossible diminish the intellectual feast we will partake in when we come to see Willa's proposals, but the cookies she makes are more than delicious! Please join us today at 4:30 in Gates 4405. Cheers Artur ---------- Forwarded message --------- From: Willa Potosnak Date: Mon, May 4, 2026 at 9:50?AM Subject: Fwd: RI PhD Thesis Proposal - Willa Potosnak To: RI People Hi everyone, Just a reminder that this is at 4:30pm today! Coffee and pastries will be provided. Best, Willa Potosnak ---------- Forwarded message --------- From: RI PhD Program Manager Date: Mon, Apr 27, 2026 at 1:52?PM Subject: RI PhD Thesis Proposal - Willa Potosnak To: RI People *RI EVENT CALENDAR* *Date: *May 4th, 2026 *Time: *4:30 PM-6:00 PM *Location*: GHC 4405 *Zoom Link* *Type: *RI PhD Thesis Proposal *Who: *Willa Potosnak *Title:* Forecasting at Scale with Efficient Deep Learning Architectures *Abstract:* Time Series Foundation Models (TSFMs) have scaled rapidly, with publicly reported pretraining corpora growing from 1.23 billion to 1 trillion data points between 2024 and 2026, an approximately 800? increase in two years. Recent work has further supplemented real-world data with synthetic data to expose models to broader time series patterns. Yet, this data-centric paradigm raises a fundamental question: *must intelligent forecasting rely solely on scale, or can intentional architectural design unlock better generalization? *This thesis proposes that more intelligently and efficiently leveraging existing data, rather than scale alone, is key to achieving better forecasting generalization. We pursue this through three parallel architectural themes: exploiting cross-channel structure beyond temporal patterns, enabling zero-shot generalization through structured composition, and reducing gradient and forecast variance by design. Each theme aims to enhance generalization with available data while treating computational efficiency as a core design principle. In this thesis, we demonstrate that scale is not the only path to generalization by: developing multivariate architectures that leverage cross-channel dependencies efficiently while reducing forecast error; showing that architectures can generalize beyond their training distribution in both patterns and concepts; and verifying variance-aware architectural designs that extract richer training signals from existing data, provably reducing gradient variance while reducing forecast error and improving calibration. Within the first theme, we further propose pretraining strategies for multivariate TSFMs to investigate whether data balancing and curriculum learning can improve downstream generalization given the same pretraining corpora. Within the second theme, we propose an additional dimension of generalization, extending beyond pattern and concept generalization to horizon generalization, an important consideration for TSFMs applied across diverse tasks and domains. Overall, this work contributes new insights into advancing time series forecasting generalization through efficient architectural design. *Committee:* Artur Dubrawski, Chair John Dolan Barnab?s P?czos Michael W. Mahoney (University of California, Berkeley) *Thesis Link* -------------- next part -------------- An HTML attachment was scrubbed... URL: From awd at cs.cmu.edu Fri May 29 14:44:32 2026 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Fri, 29 May 2026 14:44:32 -0400 Subject: A *tenured* professor Karen Chen! Message-ID: Dear Autonians, Please join me at congratulating our own Professor Karen Chen of University of Maryland Baltimore County for having her tenure approved! Karen and I met first when she missed a turn and ended up as a student in my course on Data Mining at CMU Heinz College where she was getting a masters degree in information systems management. She got my attention by asking well-pointed questions and by scoring 100% on the final exam, which only happened maybe 2-3 times in my 20 or so years teaching these courses at Heinz. Then she became a role-model staff researcher at the Auton Lab, then morphed into a PhD student, and now she is a tenured professor running a remote copy of the Auton Lab at UMBC. Not too shabby, really not too shabby Karen! Cheers, Artur -------------- next part -------------- An HTML attachment was scrubbed... URL: