We propose ESPACE, an LLM compression technique based on dimensionality reduction of activations. Unlike prior works on weight-centric tensor decomposition, ESPACE projects activations onto a pre-calibrated set of principal components. The activation-centrality of the approach enables retraining LLMs with no loss of expressivity; while at inference, weight decomposition is obtained as a byproduct of matrix multiplication associativity. Theoretical results on the construction of projection matrices with optimal computational accuracy are provided. Experimentally, we find ESPACE enables 50% compression of GPT3, Llama2, and Nemotron4 models with small accuracy degradation, as low as a 0.18 perplexity increase on GPT3-22B. At lower compression rates of 20% to 40%, ESPACE drives GPT3 models to outperforming their baseline, by up to a 0.38 decrease in perplexity for GPT3-8B. ESPACE also reduces GEMM execution time and prefill inference latency on existing hardware. Comparison with related works on compressing Llama2-7B via matrix factorization shows that ESPACE is a first step in advancing the state-of-the-art in tensor decomposition compression of LLMs.

By observing the activities and relationships of musicians and sound designers to the activities of creation, performance, publishing and dissemination with artificial intelligence (AI), from two specialized forums between 2022 and 2024, this article proposes a lexicometric analysis of the representations linked to their use. Indeed, the machine, now equipped with artificial intelligences requiring new appropriations and enabling new mediations, constitutes new challenges for artists. To study these confrontations and new mediations, our approach mobilizes the theoretical framework of the Human-AI Musicking Framework, based on a lexicometric analysis of content. The aim is to clarify the present and future uses of AI from the interfaces, in the creation of sound and musical content, and to identify the obstacles, obstacles, brakes and limits to appropriation ``in the fact of making the content one's own and integrating it as a part of oneself'' (Bachimont and Crozat, 2004) in the context of a collaboration between musician and machine.

ESP ACE projects activations onto a pre-calibrated set of principal components.

In reinforcement learning, the softmax parametrization is the standard approach for policies over discrete action spaces. However, it fails to capture the order relationship between actions. Motivated by a real-world industrial problem, we propose a novel policy parametrization based on ordinal regression models adapted to the reinforcement learning setting. Our approach addresses practical challenges, and numerical experiments demonstrate its effectiveness in real applications and in continuous action tasks, where discretizing the action space and applying the ordinal policy yields competitive performance.

We propose ESPACE, an LLM compression technique based on dimensionality reduction of activations. Unlike prior works on weight-centric tensor decomposition, ESPACE projects activations onto a pre-calibrated set of principal components. The activation-centrality of the approach enables retraining LLMs with no loss of expressivity; while at inference, weight decomposition is obtained as a byproduct of matrix multiplication associativity. Theoretical results on the construction of projection matrices with optimal computational accuracy are provided. Experimentally, we find ESPACE enables 50% compression of GPT3, Llama2, and Nemotron4 models with small accuracy degradation, as low as a 0.18 perplexity increase on GPT3-22B.

We propose ESPACE, an LLM compression technique based on dimensionality reduction of activations. Unlike prior works on weight-centric tensor decomposition, ESPACE projects activations onto a pre-calibrated set of principal components. The activation-centrality of the approach enables retraining LLMs with no loss of expressivity; while at inference, weight decomposition is obtained as a byproduct of matrix multiplication associativity. Theoretical results on the construction of projection matrices with optimal computational accuracy are provided. Experimentally, we find ESPACE enables 50% compression of GPT3, Llama2, and Nemotron4 models with small accuracy degradation, as low as a 0.18 perplexity increase on GPT3-22B. At lower compression rates of 20% to 40%, ESPACE drives GPT3 models to outperforming their baseline, by up to a 0.38 decrease in perplexity for GPT3-8B. ESPACE also reduces GEMM execution time and prefill inference latency on existing hardware. Comparison with related works on compressing Llama2-7B via matrix factorization shows that ESPACE is a first step in advancing the state-of-the-art in tensor decomposition compression of LLMs.

Recent years have witnessed an extensive popularity of convolutional neural networks (CNNs) in various computer vision and artificial intelligence applications. However, the performance gains have come at a cost of substantially intensive computation complexity, which prohibits its usage inresource-limited applications like mobile or embedded devices. While increasing attention has been paid to the acceleration of internal network structure, the redundancy of visual input is rarely considered. In this paper, we make the first attempt of reducing spatial and channel redundancy directly from the visual input for CNNs acceleration. The proposed method, termed ESPACE (Elimination of SPAtial and Channel rEdundancy), works by the following three steps: First, the 3D channel redundancy of convolutional layers is reduced by a set of low-rank approximation of convolutional filters. Second, a novel mask based selective processing scheme is proposed, which further speedups the convolution operations via skipping unsalient spatial locations of the visual input. Third, the accelerated network is fine-tuned using the training data via back-propagation. The proposed method is evaluated on ImageNet 2012 with implementations on two widely adopted CNNs, i.e. AlexNet and GoogLeNet. In comparison to several recent methods of CNN acceleration, the proposed scheme has demonstrated new state-of-the-art acceleration performance by a factor of 5.48* and 4.12* speedup on AlexNet and GoogLeNet, respectively, with a minimal decrease in classification accuracy.

Overlapping clustering problem is an important learning issue in which clusters are not mutually exclusive and each object may belongs simultaneously to several clusters. This paper presents a kernel based method that produces overlapping clusters on a high feature space using mercer kernel techniques to improve separability of input patterns. The proposed method, called OKM-K(Overlapping $k$-means based kernel method), extends OKM (Overlapping $k$-means) method to produce overlapping schemes. Experiments are performed on overlapping dataset and empirical results obtained with OKM-K outperform results obtained with OKM.