We continue to investigate input-oblivious computations and build a map of known and new complexity classes. In particular,
* We prove a new upper bound for $OL_2^P$ defined by Hirsch and Volkovich (STACS, 2026), which is a natural input-oblivious version of the $L_2^P$ class of Korten and Pitassi (FOCS, 2024): ... more >>>

The idea that learning is closely tied to compression has long served as both a powerful principle and,
at times, an informal analogy across machine learning and learning theory. Here we focus on settings in
which that intuition can be made mathematically precise, surveying formal connections among learning
algorithms, data ... more >>>

A constant-depth circuit consists of AND and OR gates of unbounded fan-in, arranged in a constant number of layers, that read the input literals; for example, a depth-three circuit is an OR of CNFs or an AND of DNFs. The classical lower bound of Håstad (1989) states that every depth-$d$ ... more >>>