Related papers: Fault Tolerance in Iterative-Convergent Machine Le…
The remarkable capabilities of Large Language Models (LLMs) often need to be tailored for specific applications, requiring the integration of new knowledge or the acquisition of new skills. While full fine-tuning is a powerful adaptation…
Learning-based navigation systems are widely used in autonomous applications, such as robotics, unmanned vehicles and drones. Specialized hardware accelerators have been proposed for high-performance and energy-efficiency for such…
Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…
Unwanted vibrations stemming from the energy-optimized design of Delta robots pose a challenge in their operation, especially with respect to precise reference tracking. To improve tracking accuracy, this paper proposes an adaptive…
Large Language Models (LLMs) are revolutionizing the AI industry with their superior capabilities. Training these models requires large-scale GPU clusters and significant computing time, leading to frequent failures that significantly…
Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…
Training large language models faces frequent interruptions due to various faults, demanding robust fault-tolerance. Existing backup-free methods, such as redundant computation, dynamic parallelism, and data rerouting, each incur…
The existing core methods, which are employed by the popular CTL model checking tools, are facing the famous state explode problem. In our previous study, a method based on the Machine Learning (ML) algorithms was proposed to address this…
Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…
The performance of battery materials is determined by their composition and the processing conditions employed during commercial-scale fabrication, where raw materials undergo complex processing steps with various additives to yield final…
Dedicated hardware accelerators are suitable for parallel computational tasks. Moreover, they have the tendency to accept inexact results. These hardware accelerators are extensively used in image processing and computer vision…
Dynamic resource allocation for machine learning workloads in cloud environments remains challenging due to competing objectives of minimizing training time and operational costs while meeting Service Level Agreement (SLA) constraints.…
Fault tolerance is a property which needs deeper consideration when dealing with streaming jobs requiring high levels of availability and low-latency processing even in case of failures where Quality-of-Service constraints must be adhered…
We analyze a fixed-point algorithm for reinforcement learning (RL) of optimal portfolio mean-variance preferences in the setting of multivariate generalized autoregressive conditional-heteroskedasticity (MGARCH) with a small penalty on…
Servo error pre-compensation and feedrate optimization are often performed independently to improve the accuracy and speed of manufacturing machines. However, this independent approach leads to unnecessary trade-offs between productivity…
Time-varying stochastic optimization problems frequently arise in machine learning practice (e.g. gradual domain shift, object tracking, strategic classification). Although most problems are solved in discrete time, the underlying process…
The existing machine learning algorithms for minimizing the convex function over a closed convex set suffer from slow convergence because their learning rates must be determined before running them. This paper proposes two machine learning…
Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance. Yet deploying these…
Supercomputing systems today often come in the form of large numbers of commodity systems linked together into a computing cluster. These systems, like any distributed system, can have large numbers of independent hardware components…
We introduce Multi-Iteration Stochastic Optimizers, a novel class of first-order stochastic methods that control the relative $L^2$ error using successive control variates along the iteration path. By exploiting correlations between…