相关论文: The Lottery Tickets Hypothesis for Supervised and …

Spiking Neural Networks (SNNs), a novel brain-inspired algorithm, are garnering increased attention for their superior computation and energy efficiency over traditional artificial neural networks (ANNs). To facilitate deployment on…

Self-supervised learning (SSL) is an approach to extract useful feature representations from unlabeled data, and enable fine-tuning on downstream tasks with limited labeled examples. Self-pretraining is a SSL approach that uses the curated…

We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that standard vision models become stable to SGD noise in this way…

Deep learning techniques have revolutionised medical imaging, improving diagnostic accuracy and enabling both more accurate and earlier disease detection. However, the relationship between pre-training strategies and downstream performance…

The training of Transformer models has revolutionized natural language processing and computer vision, but it remains a resource-intensive and time-consuming process. This paper investigates the applicability of the early-bird ticket…

The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i.e., winning tickets) that can be trained in isolation to match full accuracy. Despite many exciting efforts being made, there is one…

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…

Self-supervised learning (SSL) is used in deep learning to train on large datasets without the need for expensive labelling of the data. Recently, large Automatic Speech Recognition (ASR) models such as XLS-R have utilised SSL to train on…

Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same time run on small embedded devices, with limited hardware. While for normal size models,…

In the low-data regime, it is difficult to train good supervised models from scratch. Instead practitioners turn to pre-trained models, leveraging transfer learning. Ensembling is an empirically and theoretically appealing way to construct…

The underlying loss landscapes of deep neural networks have a great impact on their training, but they have mainly been studied theoretically due to computational constraints. This work vastly reduces the time required to compute such loss…

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

The Strong Lottery Ticket Hypothesis (SLTH) posits that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is…

This thesis delves into the intricate world of Deep Neural Networks (DNNs), focusing on the exciting concept of the Lottery Ticket Hypothesis (LTH). The LTH posits that within extensive DNNs, smaller, trainable subnetworks termed "winning…

The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for…

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i.e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions. To tackle this, adversarial training…

Pruning is a standard technique for reducing the computational cost of deep networks. Many advances in pruning leverage concepts from the Lottery Ticket Hypothesis (LTH). LTH reveals that inside a trained dense network exists sparse…

The lottery ticket hypothesis (LTH) is well-studied for convolutional neural networks but has been validated only empirically for graph neural networks (GNNs), for which theoretical findings are largely lacking. In this paper, we identify…

Deep learning models have provided extremely successful solutions in most audio application fields. However, the high accuracy of these models comes at the expense of a tremendous computation cost. This aspect is almost always overlooked in…