Riccati framework extended to multi-task learning to analytically track task interactions

ClementineDomi6 · x · 2026-11-05

Part 3 of the thread: the authors step back to study how task alignment and magnitude imbalance in the data shape learning dynamics in linear networks.

They extend the Riccati-based framework to multi-task learning, analytically characterizing how task interactions unfold across fully aligned, fully conflicting, and fully orthogonal task configurations.

Related event: TMLR paper uses Riccati framework to characterize task-interaction dynamics in multi-task learning(5 posts)→

Original post →

More from Research

• Weight-programming an MNIST MLP with coding agents: near 90% from random init — RobertTLange · 2026-11-05
• Why AI research keeps looking under the lamppost: stale problem frames inherited from Kant — fkasummer · 2026-11-05
• Engram blog: RL training complements text memory, stays robust through millions of token edits — canaesseth · 2026-11-05
• New Book on Generative AI and Stochastic Thermodynamics by Welling Team Out This Month — mjdramstead · 2026-11-05
• New paper uses 288M job postings to measure where AI raises the value of work it can't do — robseamans · 2026-11-05
• Matthew Honnibal: LLMs can 'see' weight matrices — but only one layer at a time — honnibal · 2026-11-05

Research channel →