February 2026

We consider an online learning problem in environments with multiple change points. In contrast to the single change point problem that is widely studied using classical "high confidence" detection schemes, the multiple change point environment presents new learning-theoretic and algorithmic challenges. Specifically, we show that classical methods may exhibit catastrophic failure (high regret) due to a phenomenon we refer to as endogenous confounding. To overcome this, we propose a new class of learning algorithms dubbed Anytime Tracking CUSUM […]

Ver mais

As machine learning has moved towards leveraging large models as priors for downstream tasks, the community has debated the right form of prior for solving reinforcement learning (RL) problems. If one were to try to prefetch as much computation as possible, they would attempt to learn a prior over the policies for some yet-to-be-determined reward function. Recent work (forward-backward (FB) representation learning) has tried this, arguing that an unsupervised representation learning procedure can enable optimal control over arbitrary […]

Ver mais

An AI-generated report, delivered directly to the email inboxes of journalists, was an essential tool in the Times’ coverage. It was also one of the first signals that conservative media was turning against the administration […] Built in-house and known internally as the “Manosphere Report,” the tool uses large language models (LLMs) to transcribe and summarize new episodes of dozens of podcasts. “The Manosphere Report gave us a really fast and clear signal that this was not going […]

Ver mais

Published on January 26, 2026 4:40 AM GMT This is a cross-post from https://www.250bpm.com/p/ada-palmer-inventing-the-renaissance. For over a decade, Ada Palmer, a history professor at University of Chicago (and a science-fiction writer!), struggled to teach Machiavelli. “I kept changing my approach, trying new things: which texts, what combinations, expanding how many class sessions he got…” The problem, she explains, is that “Machiavelli doesn’t unpack his contemporary examples, he assumes that you lived through it and know, so sometimes he […]

Ver mais

Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning problem over a decomposed decision space, solving position-wise bandit subproblems via adaptive expert-guided sequential construction. This formulation admits regret bounds of $O(dsqrt{T log T})$ depending on subproblem dimensionality (d) rather than combinatorial space size. On standard benchmarks, our method achieves 80–98% of specialized solvers performance while achieving two to three orders […]

Ver mais