Related papers: MILO: Model-Agnostic Subset Selection Framework fo…

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

Deep learning recommendation systems at scale have provided remarkable gains through increasing model capacity (i.e. wider and deeper neural networks), but it comes at significant training cost and infrastructure cost. Model pruning is an…

Algorithm selection and hyperparameter tuning remain two of the most challenging tasks in machine learning. Automated machine learning (AutoML) seeks to automate these tasks to enable widespread use of machine learning by non-experts. This…

To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance…

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But…

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

AI systems in high-consequence domains such as defense, intelligence, and disaster response must detect rare, high-impact events while operating under tight resource constraints. Traditional annotation strategies that prioritize label…

In this paper, we address the problem of reference tracking for uncertain nonlinear systems. Since collecting data from the target system (i.e., the system of interest) is often challenging, our objective is to design optimal controllers…

In the context of deep learning, the costliest phase from a computational point of view is the full training of the learning algorithm. However, this process is to be used a significant number of times during the design of a new artificial…

The importance of learning rate (LR) schedules on network pruning has been observed in a few recent works. As an example, Frankle and Carbin (2019) highlighted that winning tickets (i.e., accuracy preserving subnetworks) can not be found…

Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding…

Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowledge-Instructed Learning for Continual Adaptation), a novel…

Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

In the last twenty-five years (1990-2014), algorithmic advances in integer optimization combined with hardware improvements have resulted in an astonishing 200 billion factor speedup in solving Mixed Integer Optimization (MIO) problems. We…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

As the training of giant dense models hits the boundary on the availability and capability of the hardware resources today, Mixture-of-Experts (MoE) models become one of the most promising model architectures due to their significant…

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…