Related papers: Learning how to approve updates to machine learnin…

This report investigates Training Data Attribution (TDA) and its potential importance to and tractability for reducing extreme risks from AI. First, we discuss the plausibility and amount of effort it would take to bring existing TDA…

Federated fine-tuning for Large Language Models (LLMs) faces significant challenges due to the heavy communication overhead of transmitting large model updates. Although Low Rank Adaptation (LoRA) has been proposed as a solution, yet its…

Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA. Our findings suggest that the low-rank updating mechanism…

Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common…

There are many algorithms for regret minimisation in episodic reinforcement learning. This problem is well-understood from a theoretical perspective, providing that the sequences of states, actions and rewards associated with each episode…

Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and…

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient method for fine-tuning Large Langauge Models. It updates the weight matrix as $W=W_0+sBA$, where $W_0$ is the original frozen weight, $s$ is a scaling factor and $A$,$B$ are…

Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems. We study the learning…

Automatic program repair (APR) aims to reduce the manual efforts required to identify and fix errors in source code. Before the rise of LLM-based agents, a common strategy was to increase the number of generated patches, sometimes to the…

Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial perturbations, which can not only flip predictions but also…

Many high-stakes AI deployments proceed only if every stakeholder deems the system acceptable relative to their own minimum standard. With randomization over a finite menu of options, this becomes a feasibility question: does there exist a…

Robust Optimization has traditionally taken a pessimistic, or worst-case viewpoint of uncertainty which is motivated by a desire to find sets of optimal policies that maintain feasibility under a variety of operating conditions. In this…

Reinforcement learning in complex environments may require supervision to prevent the agent from attempting dangerous actions. As a result of supervisor intervention, the executed action may differ from the action specified by the policy.…

Active automata learning (AAL) algorithms can learn a behavioral model of a system from interacting with it. The primary challenge remains scaling to larger models, in particular in the presence of many possible inputs to the system. Modern…

Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…

Impressive results in natural language processing (NLP) based on the Transformer neural network architecture have inspired researchers to explore viewing offline reinforcement learning (RL) as a generic sequence modeling problem. Recent…

AI systems often struggle to provide reliable predictions across all inputs, motivating hybrid human-AI decision-making. Existing Learning to Defer (L2D) approaches address this by training models to selectively defer to human experts.…

Low-rank adaptation (LoRA) offers an efficient alternative to full-weight adaptation in federated fine-tuning of language models, significantly reducing computational costs. By adjusting ranks for each client, federated LoRA enables…

Automatic machine learning (\AML) is a family of techniques to automate the process of training predictive models, aiming to both improve performance and make machine learning more accessible. While many recent works have focused on aspects…

The limited availability of large image datasets, mainly due to data privacy and differences in acquisition protocols or hardware, is a significant issue in the development of accurate and generalizable machine learning methods in medicine.…