alphaFeedback
DJ

David Janz

cs.LGmath.PRmath.STstat.MLstat.TH

On Valency

published · living versions
W_5233a9ft·v1 · currentpublished
Does LinUCB Need Valid Confidence Sets?
with Ahmed Ben Yahmed, Marc Abeille, Clément Calauzènes
1 version

Preprints & journals

7 papers in the corpus · 2025–2026
Maximum effective dimension and information gain2608.24450v1 · David Janz, Arya Akhavan, Alexandre B. Tsybakov2026 · 0 citationsarXiv
Variance-sensitive Thompson sampling for generalised linear bandits, revisited2606.00431v1 · Tom Perneczky, Marc Abeille, David Janz2026 · 0 citationsarXiv
Sharp analysis of linear ensemble sampling2602.08026v2 · David Janz, Arya Akhavan, Csaba Szepesv'ari2026 · 0 citationsarXiv
Eluder dimension: localise it!2601.09825v3 · Alireza Bakhtiari, Alex Ayoub, Samuel Robertson et al.2026 · 0 citationsarXiv
Bernstein-type dimension-free concentration for self-normalised martingales2507.20982v2 · Arya Akhavan, Amitis Shidani, Alex Ayoub et al.2025 · 0 citationsarXiv
When and why randomised exploration works (in linear bandits)2502.08870v2 · Marc Abeille, David Janz, Ciara Pike-Burke2025 · 0 citationsarXiv
Career total: 9 works. 7 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.