We address the challenge of zeroth-order online convex optimization where the objective function’s gradient exhibits sparsity. Our aim is to …

We prove that a single layer softmax attention transformer (SAT) computes the optimal solution of canonical estimation problems in wireless …

We propose two novel distributionally robust direct preference optimization (DPO) algorithms, Wasserstein DPO (WDPO) and Kullback-Leibler DPO (KLDPO), …

We propose DiffusionBlend which enables test-time alignment of Diffusion Models to user-defined weights for objectives and regularization without …

We show that English text is a lot more compressible than what was believed to be possible previously. Our lossless compression algorithm combines the …

In coded distributed matrix multiplication, a master node wishes to compute large-scale matrix product with the help of several worker nodes, we …

Addressing the limitations of conventional scalar rewards, DOPL leverages pairwise preference feedback to navigate restless multi-armed bandit …

We explore coverless steganography using a Large Language Model (LLM) to guide an arithmetic coding decoder in generating stego-texts, aiming to embed …

We consider a wireless network where each user/sensor wishes to communicate an image to a central base station for the purpose of classifying images …

We propose a semi-blind decision-directed joint channel estimation and decoding algorithm for low-density parity check (LDPC) coded Orthogonal …