23 citations · 29 across the 9 of their papers we have counts for
10 papers
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Lazy Lagrangians with Predictions for Online Learning
Daron Anderson, George Iosifidis, Douglas J. Leith
We consider the general problem of online convex optimization with time-varying additive constraints in the presence of predictions for the next cost and constraint functions. A no…
Separable Indecomposable Continuum with Exactly One Composant
Daron Anderson
Indecomposable continua with one composant are in the sense of being non-metrisable. We adapt the method of Smith to construct an example which is $\textit{…
Indecomposable Continuum with a Strong Non-Cut Point
Daron Anderson
We construct an indecomposable continuum with exactly one strong non-cut point. The method is an adaptation of Bellamy . We start with an -chain of indecomposable metric…
The Shore Point Existence Problem is Equivalent to the Non-Block Point Existence Problem
Daron Anderson
We prove the three propositions are equivalent: Every Hausdorff continuum has two or more shore points. Every Hausdorff continuum has two or more non-block points. $(c)…
Continuum Without Non-Block Points
Daron Anderson
For any composant and corresponding near-coherence class we prove the following are equivalent : (1) properly contains a dense…
Shore and Non-Block Points in Hausdorff Continua
Daron Anderson
We study the shore and non-block points of non-metric continua. We reduce the problem of showing a continuum to have non-block points to that of showing an indecomposable continuum…
Lazy Online Gradient Descent is Universal on Polytopes
Daron Anderson, Douglas Leith
We prove the familiar Lazy Online Gradient Descent algorithm is universal on polytope domains. That means it gets pseudo-regret against i.i.d opponents, while simultaneously…
Learning The Best Expert Efficiently
Daron Anderson, Douglas J. Leith
We consider online learning problems where the aim is to achieve regret which is efficient in the sense that it is the same order as the lowest regret amongst K experts. This is a…
Optimality of the Subgradient Algorithm in the Stochastic Setting
Daron Anderson, Douglas Leith
We show that the Subgradient algorithm is universal for online learning on the simplex in the sense that it simultaneously achieves regret for adversarial costs and $O…