Related papers: Modularis: Modular Relational Analytics over Heter…
Emerging AI-enabled applications such as augmented/virtual reality (AR/VR) leverage multiple deep neural network (DNN) models for sub-tasks such as object detection, hand tracking, and so on. Because of the diversity of the sub-tasks, the…
In modern large-scale distributed systems, analytics jobs submitted by various users often share similar work, for example scanning and processing the same subset of data. Instead of optimizing jobs independently, which may result in…
The rise of Big Data has led to new demands for Machine Learning (ML) systems to learn complex models with millions to billions of parameters, that promise adequate capacity to digest massive datasets and offer powerful predictive analytics…
Network simulators play a crucial role in evaluating the performance of large-scale systems. However, existing simulators rely heavily on synthetic microbenchmarks or narrowly focus on specific domains, limiting their ability to provide…
Control architectures and autonomy stacks for complex engineering systems are often divided into layers to decompose a complex problem and solution into distinct, manageable sub-problems. To simplify designs, uncertainties are often ignored…
Background: Distributed data-intensive systems are increasingly designed to be only eventually consistent. Persistent data is no longer processed with serialized and transactional access, exposing applications to a range of potential…
In real-world machine learning deployments, models must be continually updated, composed, and when required, selectively undone. However, existing approaches to model merging and continual learning often suffer from task interference,…
Dependent Dirichlet processes (DDP) have been widely applied to model data from distributions over collections of measures which are correlated in some way. On the other hand, in recent years, increasing research efforts in machine learning…
Optimization problems often involve vector norms, which has led to extensive research on developing algorithms that can handle objectives beyond the $\ell_p$ norms. Our work introduces the concept of submodular norms, which are a versatile…
The explosive growth of multimodal data - spanning text, image, video, spatial, and relational modalities, coupled with the need for real-time semantic search and retrieval over these data - has outpaced the capabilities of existing…
The execution logs that are used for process mining in practice are often obtained by querying an operational database and storing the result in a flat file. Consequently, the data processing power of the database system cannot be used…
A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…
Synthetic data has emerged as a crucial solution to the data scarcity bottleneck in large language models (LLMs), particularly for specialized domains and low-resource languages. However, the broader adoption of existing synthetic data…
Stream reasoning systems are designed for complex decision-making from possibly infinite, dynamic streams of data. Modern approaches to stream reasoning are usually performing their computations using stand-alone solvers, which…
With FPGAs now being deployed in the cloud and at the edge, there is a need for scalable design methods which can incorporate the heterogeneity present in the hardware and software components of FPGA systems. Moreover, these FPGA systems…
We consider the problem of distributionally robust multimodal machine learning. Existing approaches often rely on merging modalities on the feature level (early fusion) or heuristic uncertainty modeling, which downplays modality-aware…
The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning strategies performed over distinct discrete architecture…
Serverless computing has attracted a broad range of applications due to its ease of use and resource elasticity. However, developing serverless applications often poses a dilemma -- relying on general-purpose serverless platforms can fall…
Relational Database Management Systems (RDBMS) manage complex, interrelated data and support a broad spectrum of analytical tasks. With the growing demand for predictive analytics, the deep integration of machine learning (ML) into RDBMS…
The rise in computing hardware choices is driving a reevaluation of operating systems. The traditional role of an operating system controlling the execution of its own hardware is evolving toward a model whereby the controlling processor is…