BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Database Systems Optimizations for Machine Learning Operations
DTSTART:20250616T143000
DTEND:20250616T163000
DTSTAMP:20261023T052305Z
UID:8a2ef90241b39f87ad5f0ed71730acdb314b80e075e4f4b5afcb4d47
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mathis Randl\nEDIC candidacy exam\nExam president: Prof. Anast
 asia Ailamaki\nThesis advisor: Prof. Anne-Marie Kermarrec\nCo-examiner: Pr
 of. Sanidhya Kashyap\n\nAbstract\nRecent machine learning systems increasi
 ngly rely on retrieving information from large external corpora at inferen
 ce time. This report examines three key papers that define and refine the 
 design of such retrieval-based architectures across different system level
 s. The first\, Retrieval-Augmented Generation (RAG)\, introduces a hybrid 
 model that combines dense retrieval with neural generation to improve fact
 ual accuracy and interpretability in knowledge-intensive NLP tasks. The se
 cond\, FAISS\, addresses the scalability challenges of dense vector search
  by proposing an efficient approximate nearest neighbor (ANN) framework op
 timized for GPU execution. The third\, JUNO\, further accelerates ANN sear
 ch by leveraging sparsity in product quantization and mapping filtering op
 erations to ray tracing cores. Together\, these papers trace a progression
  from algorithmic design to systems optimization and finally to hardware-a
 ware acceleration. The report concludes with a discussion of open challeng
 es and outlines a research direction building on these foundations.\n\nSel
 ected papers\n1. Retrieval-Augmented Generation for Knowledge-Intensive NL
 P Tasks\, Lewis et al\, https://proceedings.neurips.cc/paper/2020/hash/6b4
 93230205f780e1bc26945df7481e5-Abstract.html\n\n2. Billion-Scale Similarity
  Search with GPUs\, Johnson et al\, https://ieeexplore.ieee.org/document/8
 733051\n\n3. JUNO: Optimizing High-Dimensional Approximate Nearest Neighbo
 ur Search with Sparsity-Aware Algorithm and Ray-Tracing Core Mapping\, Liu
  et al\, https://dl.acm.org/doi/10.1145/3620665.3640360\n 
LOCATION:BC 233 https://plan.epfl.ch/?room==BC%20233
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR