Low-precision networks, with weights and activations quantized to low bit-width, are widely used to accelerate inference on edge devices. However, current solutions are uniform, using identical bit-width for all filters. This fails to account for the different sensitivities of different filters and is suboptimal. Mixed-precision networks address this problem, by tuning the bit-width to individual filter requirements. In this work, the problem of optimal mixed-precision network search (MPS) is considered. To circumvent its difficulties of discrete search space and combinatorial optimization, a new differentiable search architecture is proposed, with several novel contributions to advance the efficiency by leveraging the unique properties of the MPS problem. The resulting Efficient differentiable MIxed-Precision network Search (EdMIPS) method is effective at finding the optimal bit allocation for multiple popular networks, and can search a large model, e.g. Inception-V3, directly on ImageNet without proxy task in a reasonable amount of time. The learned mixed-precision networks significantly outperform their uniform counterparts.
Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly optimizing the model weight and architecture parameters in a weight-sharing supernet via gradient-based algorithms. At the end of the search phase, the operations with the largest architecture parameters will be selected to form the final architecture, with the implicit assumption that the values of architecture parameters reflect the operation strength. While much has been discussed about the supernet's optimization, th…
Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）
Differentiable simulation is a promising toolkit for fast gradient-based policy optimization and system identification. However, existing approaches to differentiable simulation have largely tackled scenarios where obtaining smooth gradients has been relatively easy, such as systems with mostly smooth dynamics. In this work, we study the challenges that differentiable simulation presents when it is not feasible to expect that a single descent reaches a global optimum, which is often a problem in contact-rich scenarios. We analyze the optimization landscapes of diverse scenarios that contain bo…
In this paper, we propose a mixed-precision convolution unit architecture which supports different integer and floating point (FP) precisions. The proposed architecture is based on low-bit inner product units and realizes higher precision based on temporal decomposition. We illustrate how to integrate FP computations on integer-based architecture and evaluate overheads incurred by FP arithmetic support. We argue that alignment and addition overhead for FP inner product can be significant since the maximum exponent difference could be up to 58 bits, which results into a large alignment logic. T…
Hong Kong University of Science and Technology（香港科技大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Jockey Club Institute for Advanced Study, HKUST（香港科技大学赛马会高等研究院）；Reality Labs, Meta Inc（Meta公司现实实验室）；ACCESS - AI Chip Center for Emerging Smart Systems（新兴智能系统AI芯片中心（ACCESS））；Carnegie Mellon University（卡内基梅隆大学）
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed precision quantization (MPQ) begins to fully leverage the capacity of representation by searching optimized bitwidths for different layers and modules in a network. However, previous studies mainly search the MPQ strategy in a costly scheme using reinforcement learning, neural architecture search, etc., or simply utilize partial prior knowledge for bitwidth assignm…
The Chinese University of Hong Kong（香港中文大学）；SenseBrain, Ltd（SenseBrain有限公司）；Shanghai AI Lab（上海人工智能实验室）；The University of Hong Kong（香港大学）
Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune these values, we present a fully differentiable approach to learn all of them, named Differentiable Dynamic Quantization (DDQ), which has several benefits. (1) DDQ is able to quantize challenging lightweight architectures like MobileNets, where different layers prefer different quantization parameters. (2) DDQ is hardware-friendly and can be easily implement…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underlying mechanism of several existing differentiable NAS frameworks. Our investigation is motivated by three observed searching patterns of differentiable NAS: 1) they search by growing instead of pruning; 2) wider networks are more preferred than deeper ones; 3) no edges are selected in bi-level optimization. To anatomize these phenomena, we propose a unified view on searching algorithms of existing frameworks, transfe…
$\texttt{immrax}$: A Parallelizable and Differentiable Toolbox for Interval Analysis and Mixed Monotone Reachability in JAX
School of Electrical and Computer Engineering, Georgia Institute of Technology（佐治亚理工学院电气与计算机工程学院）；Department of Electrical, Computer, and Energy Engineering, University of Colorado, Boulder（科罗拉多大学博尔德分校电气、计算机与能源工程系）
Rethinking Nonlinearity: Trainable Gaussian Mixture Modules for Modern Neural Architectures
Guangdong Institute of Intelligence Science and Technology（广东智能科学与技术研究院）；Great Bay University（大湾大学）；University of Massachusetts at Amherst（马萨诸塞大学阿姆赫斯特分校）
SenseTime Research（商汤科技研究院）；Peking University（北京大学）；University of Science and Technology Beijing（北京科技大学）
Emergent hardwares can support mixed precision CNN models inference that assign different bitwidths for different layers. Learning to find an optimal mixed precision model that can preserve accuracy and satisfy the specific constraints on model size and computation is extremely challenge due to the difficult in training a mixed precision model and the huge space of all possible bit quantizations. In this paper, we propose a novel soft Barrier Penalty based NAS (BP-NAS) for mixed precision quantization, which ensures all the searched models are inside the valid domain defined by the complexity …
We present a differentiable formulation of abstract chemical reaction networks (CRNs) that can be trained to solve a variety of computational tasks. Chemical reaction networks are one of the most fundamental computational substrates used by nature. We study well-mixed single-chamber systems, as well as systems with multiple chambers separated by membranes, under mass-action kinetics. We demonstrate that differentiable optimisation, combined with proper regularisation, can discover non-trivial sparse reaction networks that can implement various sorts of oscillators and other chemical computing …
Rethinking Input Domains in Physics-Informed Neural Networks via Geometric Compactification Mappings
School of Information and Software Engineering, University of Electronic Science and Technology of China（信息与软件工程学院，电子科学与技术大学）；Computer Science and Engineering, University of Electronic Science and Technology of China（计算机科学与工程，电子科学与技术大学）；Institute of Software Chinese Academy of Sciences, Beijing, China（软件研究所，中国科学院北京）；School of Robotics and Advanced Manufacture, Harbin Institute of Technology, Shenzhen, China（机器人与先进制造学院，哈尔滨工业大学深圳）
Probabilistic programs with mixed support (both continuous and discrete latent random variables) commonly appear in many probabilistic programming systems (PPSs). However, the existence of the discrete random variables prohibits many basic gradient-based inference engines, which makes the inference procedure on such models particularly challenging. Existing PPSs either require the user to manually marginalize out the discrete variables or to perform a composing inference by running inference separately on discrete and continuous variables. The former is infeasible in most cases whereas the lat…
Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mamba
National Key Laboratory of Big Data and Decision, National University of Defense Technology（大数据与决策国家重点实验室，国防科技大学）；School of Computer Science, South China University of Technology（华南理工大学计算机科学学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理学院计算机与信息系统学院）
Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a same value empirically, which limits the predictive performance of latent factor models. Existing works have proposed heuristic or reinforcement learning-based methods to search for mixed feature embedding dimensions. For efficiency concern, these methods typically choose embedding dimensions from a restricted set of candidate dimensions. However, this restric…
Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the exact quantization scheme. Previous methods either examine only a small manually-designed search space or utilize a cumbersome neural architecture search to explore the vast search space. These approaches cannot lead to an optimal quantization scheme efficiently. This work proposes bit-level sparsity quantization (BSQ) to tackle the mixed-precision quantization …
As neural networks grow deeper and wider, learning networks with hard-threshold activations is becoming increasingly important, both for network quantization, which can drastically reduce time and energy requirements, and for creating large integrated systems of deep networks, which may have non-differentiable components and must avoid vanishing and exploding gradients for effective learning. However, since gradient descent is not applicable to hard-threshold functions, it is not clear how to learn networks of them in a principled way. We address this problem by observing that setting targets …
Qualcomm AI Research（高通人工智能研究院）；University of California, Irvine（加利福尼亚大学尔湾分校）
We present a differentiable joint pruning and quantization (DJPQ) scheme. We frame neural network compression as a joint gradient-based optimization problem, trading off between model pruning and quantization automatically for hardware efficiency. DJPQ incorporates variational information bottleneck based structured pruning and mixed-bit precision quantization into a single differentiable loss function. In contrast to previous works which consider pruning and quantization separately, our method enables users to find the optimal trade-off between both in a single training procedure. To utilize …
Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwidths is not straight forward, training methods, which can learn them, are desirable. Differentiable quantization with straight-through gradients allows to learn the quantizer's parameters using gradient methods. We show that a suited parametrization of the quantizer is the key to…
Xi’an Jiaotong University（西安交通大学）；The Hong Kong Polytechnic University（香港理工大学）
Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static quality-consistent training setting, i.e., all data is assumed to be of the same quality across training and inference, overlooks data quality changes in real-world applications which may lead to poor robustness of the quantized models. In this paper, we propose a novel Data Quality-aware Mixed-precision Quantization framework, dubbed DQMQ, to dynamically adapt quanti…
Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization
School of Computer and Communication Engineering, Northeastern University（东北大学计算机与通信工程学院）；School of Software Engineering, Beijing Jiaotong University（北京交通大学软件工程学院）；School of Software, Northeastern University（东北大学软件学院）
Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
College of Software, Northeastern University（东北大学软件学院）；Institute of Intelligent Manufacturing, Nanjing Tech University（南京科技大学智能制造研究院）；Faculty of Engineering, University of Toyama（东大大学工学院）
Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection
TUM School of Management, Technical University of Munich（慕尼黑工业大学TUM管理学院）；Esade, Ramon Llull University（拉蒙·柳利大学ESADE商学院）；Munich Data Science Institute (MDSI), Technical University of Munich（慕尼黑工业大学慕尼黑数据科学研究所）
Department of Statistics, Columbia University, New York, USA（哥伦比亚大学统计系，纽约，美国）；Department of Computer Science, Columbia University, New York, USA（哥伦比亚大学计算机科学系，纽约，美国）
DFSC: Error-Controlled Differentiable Mittag-Leffler Propagation for Fractional Scientific Machine Learning
School of Mechanical Engineering, Hangzhou Dianzi University（杭州电子科技大学机械工程学院）；School of Computer Science, Hangzhou Dianzi University（杭州电子科技大学计算机学院）；School of Mathematics and Physics, Xi’an Jiaotong-Liverpool University（西交利物浦大学数学与物理学院）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
