Related papers: Winner-Take-All Column Row Sampling for Memory Eff…
Large Language Models (LLMs) exhibit substantial parameter redundancy, particularly in Feed-Forward Networks (FFNs). Existing pruning methods suffer from two primary limitations. First, reliance on dataset-specific calibration introduces…
Large Language Models (LLMs) have achieved remarkable success with their billion-level parameters, yet they incur high inference overheads. The emergence of activation sparsity in LLMs provides a natural approach to reduce this cost by…
The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a…
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…
A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…
Retrieval-augmented generation (RAG) has become a widely recognized paradigm to combine parametric memory with non-parametric memories. An RAG model consists of two serial connecting components (retriever and generator). A major challenge…
Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…
The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…
In this paper we propose to use the Winner Takes All hashing technique to speed up forward propagation and backward propagation in fully connected layers in convolutional neural networks. The proposed technique reduces significantly the…
Transformer-based models have become the \textit{de facto} backbone across many fields, such as computer vision and natural language processing. However, as these models scale in size, external memory access (EMA) for weight and activations…
Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…
Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…
Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away…
Fast and efficient AI inference is increasingly important, and recent models that directly learn low-level logic operations have achieved state-of-the-art performance. However, existing logic neural networks incur high training costs,…
Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory…
Low-rank architectures have become increasingly important for efficient large language model (LLM) pre-training, providing substantial reductions in both parameter complexity and memory/computational demands. Despite these advantages,…
The Tsetlin Machine (TM) is an interpretable mechanism for pattern recognition that constructs conjunctive clauses from data. The clauses capture frequent patterns with high discriminating power, providing increasing expression power with…
We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…
Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or…
Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), and Memory Networks which contain memory are popularly used to learn patterns in sequential data. Sequential data has long sequences that hold relationships. RNN can…