Related papers: PARQ: Piecewise-Affine Regularized Quantization
Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…
We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than…
Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discretization before the…
Feature selection identifies subsets of informative features and reduces dimensions in the original feature space, helping provide insights into data generation or a variety of domain problems. Existing methods mainly depend on feature…
Reinforcement learning algorithms have become more complex since the invention of target networks. Unfortunately, target networks have not kept up with this increased complexity, instead requiring approximate solutions to be computationally…
Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to…
We present a proximal augmented Lagrangian based solver for general convex quadratic programs (QPs), relying on semismooth Newton iterations with exact line search to solve the inner subproblems. The exact line search reduces in this case…
Classical supervised classification tasks search for a nonlinear mapping that maps each encoded feature directly to a probability mass over the labels. Such a learning framework typically lacks the intuition that encoded features from the…
Offline reinforcement learning (RL), which optimizes policies using a previously collected static dataset, is an important branch of RL. A popular and promising approach is to regularize actor-critic methods with behavior cloning (BC),…
We consider the problem of learning a linear factor model. We propose a regularized form of principal component analysis (PCA) and demonstrate through experiments with synthetic and real data the superiority of resulting estimates to those…
Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…
We propose a novel SPARsity and Clustering (SPARC) regularizer, which is a modified version of the previous octagonal shrinkage and clustering algorithm for regression (OSCAR), where, the proposed regularizer consists of a $K$-sparse…
In this work we describe an Adaptive Regularization using Cubics (ARC) method for large-scale nonconvex unconstrained optimization using Limited-memory Quasi-Newton (LQN) matrices. ARC methods are a relatively new family of optimization…
Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model…
For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough results, they are often…
We present an extension of sparse PCA, or sparse dictionary learning, where the sparsity patterns of all dictionary elements are structured and constrained to belong to a prespecified set of shapes. This \emph{structured sparse PCA} is…
One of the main challenges in ranking is embedding the query and document pairs into a joint feature space, which can then be fed to a learning-to-rank algorithm. To achieve this representation, the conventional state of the art approaches…
Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained devices. However, it is still hard for extremely low-bit…
Machine learning algorithms use error function minimization to fit a large set of parameters in a preexisting model. However, error minimization eventually leads to a memorization of the training dataset, losing the ability to generalize to…
To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous…