collaborators

6 papers

cs.LG2026

From Score Approximation to Distribution Approximation in Score-Based Diffusion Models

Lan V. Truong

Score-based diffusion models have achieved remarkable empirical success in generative modeling, yet their approximation-theoretic foundations remain incomplete. In particular, alth…

cs.LG2026

Asymptotic Signal Subspace Recovery in Softmax Attention Models

Lan V. Truong

Attention mechanisms have demonstrated remarkable empirical success in identifying relevant information from large collections of tokens, yet the theoretical principles underlying…

math.OC2026

On the Induced Norms of Matrices and Grothendieck problems

Lan V. Truong, M. H. Duong

We study the induced matrix norm $\|\bA\|_{q \to r}$, whose exact value has been known only in a few classical cases. Determining this norm has long been regarded as difficult due…

cs.LG2026

Transformers Learn Robust In-Context Regression under Distributional Uncertainty

Hoang T. H. Cao, Hai D. V. Trinh, Tho Quan +1

Recent work has shown that Transformers can perform in-context learning for linear regression under restrictive assumptions, including i.i.d. data, Gaussian noise, and Gaussian reg…

cs.LG2026

Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima

Lan V. Truong

We study best-arm identification in stochastic multi-armed bandits under the fixed-confidence setting, focusing on instances with multiple optimal arms. Unlike prior work that addr…

stat.ML2024

On Rank-Dependent Generalisation Error Bounds for Transformers

Lan V. Truong

In this paper, we introduce various covering number bounds for linear function classes, each subject to different constraints on input and matrix norms. These bounds are contingent…