Related papers: Fast Benchmarking of Asynchronous Multi-Fidelity O…
Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reasoning regardless of problem complexity. We present…
The aim of the paper is to introduce general techniques in order to optimize the parallel execution time of sorting on a distributed architectures with processors of various speeds. Such an application requires a partitioning step. For…
Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context…
Choosing a suitable ML model is a complex task that can depend on several objectives, e.g., accuracy, fairness, or energy consumption. In practice, this requires trading off multiple, often competing, objectives through multi-objective…
Uncertainty quantification for estimation through stochastic optimization solutions in an online setting has gained popularity recently. This paper introduces a novel inference method focused on constructing confidence intervals with…
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming. In addition to the computational effort required, this process also requires some ancillary efforts including…
Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its reliance on a reference policy introduces a critical tension. DPO weighs each update relative to a…
Planning under uncertainty is critical for robust robot performance in uncertain, dynamic environments, but it incurs high computational cost. State-of-the-art online search algorithms, such as DESPOT, have vastly improved the computational…
Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…
Simultaneous speech translation (SST) generates translations while receiving partial speech input. Recent advances show that large language models (LLMs) can substantially improve SST quality, but at the cost of high computational overhead.…
We present HIghly Parallelisable Pareto Optimisation (HIPPO) -- a batch acquisition function that enables multi-objective Bayesian optimisation methods to efficiently exploit parallel processing resources. Multi-Objective Bayesian…
Traditional heterogeneous parallel algorithms, designed for heterogeneous clusters of workstations, are based on the assumption that the absolute speed of the processors does not depend on the size of the computational task. This assumption…
Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency. Despite its impressive success so far, it is still unclear how to appropriately schedule the important hyperparameters to achieve…
Modern data analytical workloads often need to run queries over a large number of tables. An optimal query plan for such queries is crucial for being able to run these queries within acceptable time bounds. However, with queries involving…
Recent advances in derivative-free optimization allow efficient approximation of the global-optimal solutions of sophisticated functions, such as functions with many local optima, non-differentiable and non-continuous functions. This…
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization (muP), many optimal HPs…
Hyper-parameter optimization is crucial for pushing the accuracy of a deep learning model to its limits. A hyper-parameter optimization job, referred to as a study, involves numerous trials of training a model using different training…
We present a novel parallelisation scheme that simplifies the adaptation of learning algorithms to growing amounts of data as well as growing needs for accurate and confident predictions in critical applications. In contrast to other…
Fault tolerance overhead of high performance computing (HPC) applications is becoming critical to the efficient utilization of HPC systems at large scale. HPC applications typically tolerate fail-stop failures by checkpointing. Another…
Diffusion probabilistic models have set a new standard for generative fidelity but are hindered by a slow iterative sampling process. A powerful training-free strategy to accelerate this process is Schedule Optimization, which aims to find…