Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o,
have captured significant attention in the speech domain. Compared to traditional three-tier …

We present an optimal method for encoding cluster assignments of arbitrary data sets. Our
method, Random Cycle Coding (RCC), encodes data sequentially and sends assignment …

Machine learning and vector search are two research topics that developed in parallel in
nearby communities. However, unlike many other fields related to big data, machine …

Vector Quantized Variational AutoEncoder (VQ-VAE) is an established technique in
machine learning for learning discrete representations across various modalities. However …

Vector quantization is a technique in machine learning that discretizes continuous
representations into a set of discrete vectors. It is widely employed in tokenizing data …

Approximate nearest neighbor search for vectors relies on indexes that are most often
accessed from RAM. Therefore, storage is the factor limiting the size of the database that can …

The dimensionality of the embedding and the number of available embeddings (also called
codebook size) are critical factors influencing the performance of Vector Quantization (VQ), a …

Vector quantization is a fundamental technique for compression and large-scale nearest
neighbor search. For high-accuracy operating points, multi-codebook quantization …

This thesis deals with the problem of communicating and storing non-sequential data. We
investigate this problem through the lens of lossless source coding, also sometimes referred …