Related papers: Length-Adaptive Transformer: Train Once with Lengt…

End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different…

End-to-end training with full-depth backpropagation remains the dominant paradigm for optimizing deep neural networks, but its efficiency deteriorates as models grow deeper. Since every block must be executed and differentiated under a…

In unsupervised learning, collecting more data is not always a costly process unlike the training. For example, it is not hard to enlarge the 40GB WebText used for training GPT-2 by modifying its sampling methodology considering how many…

Current state-of-the-art results in computer vision depend in part on fine-tuning large pre-trained vision models. However, with the exponential growth of model sizes, the conventional full fine-tuning, which needs to store a individual…

Few-shot learning and parameter-efficient fine-tuning (PEFT) are crucial to overcome the challenges of data scarcity and ever growing language model sizes. This applies in particular to specialized scientific domains, where researchers…

A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this…

Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are…

Large language models (LLMs) are increasingly capable of completing knowledge intensive tasks by recalling information from a static pretraining corpus. Here we are concerned with LLMs in the context of evolving data requirements. For…

Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a $\textit{manually}$ defined learning rate schedule, i.e., the learning rate is dropped at the pre-defined epochs, typically when the…

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectories from datasets,…

Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases,…

Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different…

With the breakthrough of Transformer-based pre-trained models, the demand for fine-tuning (FT) to adapt the base pre-trained models to downstream applications continues to grow, so it is essential for service providers to reduce the cost of…

Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training…

Originally, dropout was seen as a breakthrough regularization technique that reduced overfitting and improved performance in almost all applications of deep learning by reducing overfitting. Yet, single-epoch pretraining tasks common to…

Fine-tuning a pretrained transformer for a downstream task has become a standard method in NLP in the last few years. While the results from these models are impressive, applying them can be extremely computationally expensive, as is…

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…