Related papers: Endure: A Robust Tuning Paradigm for LSM Trees Und…

In robust optimization one seeks to make a decision under uncertainty, where the goal is to find the solution with the best worst-case performance. The set of possible realizations of the uncertain data is described by a so-called…

Large language models (LLMs) require substantial computational resources, leading to significant carbon emissions and operational costs. Although training is energy-intensive, the long-term environmental burden arises from inference,…

LLMs have seen rapid adoption in all domains. They need to be trained on high-end high-performance computing (HPC) infrastructures and ingest massive amounts of input data. Unsurprisingly, at such a large scale, unexpected events (e.g.,…

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…

Cloud computing has grown rapidly in recent years, mainly due to the sharp increase in data transferred over the internet. This growth makes load balancing a key part of cloud systems, as it helps distribute user requests across servers to…

This work proposes a framework for multistage adjustable robust optimization that unifies the treatment of three different types of endogenous uncertainty, where decisions, respectively, (i) alter the uncertainty set, (ii) affect the…

Ultra-large scale (ULS) systems are becoming pervasive. They are inherently complex, which makes their design and control a challenge for traditional methods. Here we propose the design and analysis of ULS systems using measures of…

In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture…

Modern databases typically makes use of the Log Structured Merge-Tree for organizing data in indexes, which is a kind of disk-based data structure. It was proposed to efficiently handle frequent update queries (also called update intensive…

To achieve high performance of a machine learning (ML) task, a deep learning-based model must implicitly capture the entire distribution from data. Thus, it requires a huge amount of training samples, and data are expected to fully present…

Future Mobile Networks (MNs), 5G and beyond 5G, will require a paradigm shift from traditional resource allocation mechanisms as Base Stations (BSs) will be empowered with computation capabilities (i.e., offloading and computation is…

Large language models (LLMs) have achieved significant progress across various domains, but their increasing scale results in high computational and memory costs. Recent studies have revealed that LLMs exhibit sparsity, providing the…

The log-structured merge tree (LSM-tree) is widely employed to build key-value (KV) stores. LSM-tree organizes multiple levels in memory and on disk. The compaction of LSM-tree, which is used to redeploy KV pairs between on-disk levels in…

The Learning Rate (LR) has a high impact on deep learning training performance. A common practice is to train a Deep Neural Network (DNN) multiple times with different LR policies to find the optimal LR policy, which has been widely…

Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LLMs directly to temporal data introduces a modality gap: text tokenizers fragment…

The increasing proliferation of IoT devices and AI applications has created a demand for scalable and efficient computing solutions, particularly for applications requiring real-time processing. The compute continuum integrates edge and…

Distributed multi-controller deployment is a promising method to achieve a scalable and reliable control plane of Software-Defined Networking (SDN). However, it brings a new challenge for balancing loads on the distributed controllers as…

Database Management Systems and K/V-Stores operate on updatable datasets -- massively exceeding the size of available main memory. Tree-based K/V storage management structures became particularly popular in storage engines. B+ Trees allow…

Large language models (LLMs) can generate programs that pass unit tests, but passing tests does not guarantee reliable runtime behavior. We find that different correct solutions to the same task can show very different memory and…

Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference pipelines make elastic serving challenging. Existing…