This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization, from a stochastic differential equation perspective. We show that DMs can be conceptualized by reversing a stochastic process driven by the Langevin equation, which then produces samples from an initial distribution to approximate the target distribution. In a toy model, we highlight the capability of DMs to learn effective actions. Furthermore, we demonstrate its feasibility to act as a global sampler for generating configurations in the two-dimensional $\phi^4$ quantum lattice field theory.
Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques. Such algorithms typically learn continuous embeddings of the data. To avoid a subsequent costly binarization step, a common solution is to employ loss functions that combine a similarity learning term (to ensure similar images are grouped to nearby embeddings) and a quantization penalty term (to ensure that the embedding entries are close to binarized entries, e.g., -1 or 1). Still, the interaction between these two terms can make learning harder and the embeddings worse. We propose an alternative quantization strategy that decomposes the learning problem in two stages: first, perform similarity learning over the embedding space with no quantization; second, find an optimal orthogonal transformation of the embeddings so each coordinate of the embedding is close to its sign, and then quantize the transformed embedding through the sign function. In the second step, we parametrize orthogonal transformations using Householder matrices to efficiently leverage stochastic gradient descent. Since similarity measures are usually invariant under orthogonal transformations, this quantization strategy comes at no cost in terms of performance. The resulting algorithm is unsupervised, fast, hyperparameter-free and can be run on top of any existing deep hashing or metric learning algorithm. We provide extensive experimental results showing that this approach leads to state-of-the-art performance on widely used image datasets, and, unlike other quantization strategies, brings consistent improvements in performance to existing deep hashing algorithms.
In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing convolutional modules with self-attention modules. They achieve state-of-the-art performance on ASR with top efficiency. We first show that employing these speech transformers as an encoder significantly improves the efficiency of pre-trained audio models as well. However, our study shows that we can achieve comparable efficiency with advanced self-attention solely. We demonstrate that this simpler approach is particularly beneficial with a low-bit weight quantization technique of a neural network to improve efficiency. We hypothesize that it prevents propagating the errors between different quantized modules compared to recent speech transformers mixing quantized convolution and the quantized self-attention modules.
We propose a data-driven approach to explicitly learn the progressive encoding of a continuous source, which is successively decoded with increasing levels of quality and with the aid of correlated side information. This setup refers to the successive refinement of the Wyner-Ziv coding problem. Assuming ideal Slepian-Wolf coding, our approach employs recurrent neural networks (RNNs) to learn layered encoders and decoders for the quadratic Gaussian case. The models are trained by minimizing a variational bound on the rate-distortion function of the successively refined Wyner-Ziv coding problem. We demonstrate that RNNs can explicitly retrieve layered binning solutions akin to scalable nested quantization. Moreover, the rate-distortion performance of the scheme is on par with the corresponding monolithic Wyner-Ziv coding approach and is close to the rate-distortion bound.
Large Language Models (LLMs) have reshaped natural language processing with their impressive capabilities. However, their ever-increasing size has raised concerns about their effective deployment and the need for LLM compression. This study introduces the Divergent Token Metrics (DTMs), a novel approach to assessing compressed LLMs, addressing the limitations of traditional perplexity or accuracy measures that fail to accurately reflect text generation quality. DTMs measure token divergences that allow deeper insights into the subtleties of model compression, in particular, when evaluating components' impacts individually. Utilizing the First Divergent Token Metric (FDTM) in model sparsification reveals that 25% of all attention components can be pruned beyond 90% on the Llama-2 model family, still keeping SOTA performance. For quantization, FDTM suggests that more than 80% of parameters can be naively transformed to int8 without special outlier management. These evaluations indicate the necessity of choosing appropriate compressions for parameters individually -- and that FDTM can identify those -- while standard metrics result in deteriorated outcomes.
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point (FP) formats show good performance in LLM quantization, they tend to perform poorly with small group sizes or sub-4 bits. We find the reason is that the absence of asymmetry in previous FP quantization makes it unsuitable for handling asymmetric value distribution of LLM weight tensors. In this work, we propose asymmetric FP quantization (AFPQ), which sets separate scales for positive and negative values. Our method leads to large accuracy improvements and can be easily plugged into other quantization methods, including GPTQ and AWQ, for better performance. Besides, no additional storage is needed compared with asymmetric integer (INT) quantization. The code is available at https://github.com/zhangsichengsjtu/AFPQ.
In this paper, we investigate tracking control of heterogeneous multi-agent systems under Denial-of-Service (DoS) attacks and state quantization. Dynamic quantized mechanisms are designed for inter-follower communication and leader-follower communication. Zooming-in and out factors, and data rates of both mechanisms for preventing quantizer saturation are provided. Our results show that by tuning the inter-follower quantized controller, one cannot improve the resilience beyond a level determined by the data rate of leader-follower quantized communication, i.e., the ceiling effect. Otherwise, overflow of followers' state quantizer can occur. On the other hand, if one selects a "large" data rate for leader-follower quantized communication, then the inter-follower quantized communication determines the resilience, and further increasing the data rate for leader-follower quantized communication cannot improve the resilience, i.e., the bottleneck effect. Simulation examples are provided to justify the results of our paper.
Large language models(LLMs) exhibit excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. However, existing methods struggle to strike a balance between model accuracy and hardware efficiency. This is where we introduce AWEQ, a post-training method that requires no additional training overhead. AWEQ excels in both ultra-low-bit quantization and 8-bit weight and activation (W8A8) quantization. There is an observation that weight quantization is less challenging than activation quantization. AWEQ transfers the difficulty of activation quantization to weights using channel equalization, achieving a balance between the quantization difficulties of both, and thereby maximizing performance. We have further refined the equalization method to mitigate quantization bias error, ensuring the robustness of the model. Extensive experiments on popular models such as LLaMA and OPT demonstrate that AWEQ outperforms all existing post-training quantization methods for large models.
Crops hold paramount significance as they serve as the primary provider of energy, nutrition, and medicinal benefits for the human population. Plant diseases, however, can negatively affect leaves during agricultural cultivation, resulting in significant losses in crop output and economic value. Therefore, it is crucial for farmers to identify crop diseases. However, this method frequently necessitates hard work, a lot of planning, and in-depth familiarity with plant pathogens. Given these numerous obstacles, it is essential to provide solutions that can easily interface with mobile and IoT devices so that our farmers can guarantee the best possible crop development. Various machine learning (ML) as well as deep learning (DL) algorithms have been created & studied for the identification of plant disease detection, yielding substantial and promising results. This article presents a novel classification method that builds on prior work by utilising attention-based feature extraction, RGB channel-based chromatic analysis, Support Vector Machines (SVM) for improved performance, and the ability to integrate with mobile applications and IoT devices after quantization of information. Several disease classification algorithms were compared with the suggested model, and it was discovered that, in terms of accuracy, Vision Transformer-based feature extraction and additional Green Chromatic Coordinate feature with SVM classification achieved an accuracy of (GCCViT-SVM) - 99.69%, whereas after quantization for IoT device integration achieved an accuracy of - 97.41% while almost reducing 4x in size. Our findings have profound implications because they have the potential to transform how farmers identify crop illnesses with precise and fast information, thereby preserving agricultural output and ensuring food security.
Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which requires a demand for large memory capacity and high memory bandwidth. In this paper, we propose an effective approach that can make the deployment of LLMs more efficiently. We support an automatic INT4 weight-only quantization flow and design a special LLM runtime with highly-optimized kernels to accelerate the LLM inference on CPUs. We demonstrate the general applicability of our approach on popular LLMs including Llama2, Llama, GPT-NeoX, and showcase the extreme inference efficiency on CPUs. The code is publicly available at: https://github.com/intel/intel-extension-for-transformers.
As a primary contribution, we present a convergence theorem for stochastic iterations, and in particular, Q-learning iterates, under a general, possibly non-Markovian, stochastic environment. Our conditions for convergence involve an ergodicity and a positivity criterion. We provide a precise characterization on the limit of the iterates and conditions on the environment and initializations for convergence. As our second contribution, we discuss the implications and applications of this theorem to a variety of stochastic control problems with non-Markovian environments involving (i) quantized approximations of fully observed Markov Decision Processes (MDPs) with continuous spaces (where quantization break down the Markovian structure), (ii) quantized approximations of belief-MDP reduced partially observable MDPS (POMDPs) with weak Feller continuity and a mild version of filter stability (which requires the knowledge of the model by the controller), (iii) finite window approximations of POMDPs under a uniform controlled filter stability (which does not require the knowledge of the model), and (iv) for multi-agent models where convergence of learning dynamics to a new class of equilibria, subjective Q-learning equilibria, will be studied. In addition to the convergence theorem, some implications of the theorem above are new to the literature and others are interpreted as applications of the convergence theorem. Some open problems are noted.
Among applications of deep learning (DL) involving low cost sensors, remote image classification involves a physical channel that separates edge sensors and cloud classifiers. Traditional DL models must be divided between an encoder for the sensor and the decoder + classifier at the edge server. An important challenge is to effectively train such distributed models when the connecting channels have limited rate/capacity. Our goal is to optimize DL models such that the encoder latent requires low channel bandwidth while still delivers feature information for high classification accuracy. This work proposes a three-step joint learning strategy to guide encoders to extract features that are compact, discriminative, and amenable to common augmentations/transformations. We optimize latent dimension through an initial screening phase before end-to-end (E2E) training. To obtain an adjustable bit rate via a single pre-deployed encoder, we apply entropy-based quantization and/or manual truncation on the latent representations. Tests show that our proposed method achieves accuracy improvement of up to 1.5% on CIFAR-10 and 3% on CIFAR-100 over conventional E2E cross-entropy training.
Recent advancements in unsupervised protein language models (ProteinLMs), like ESM-1b and ESM-2, have shown promise in different protein prediction tasks. However, these models face challenges due to their high computational demands, significant memory needs, and latency, restricting their usage on devices with limited resources. To tackle this, we explore post-training quantization (PTQ) for ProteinLMs, focusing on ESMFold, a simplified version of AlphaFold based on ESM-2 ProteinLM. Our study is the first attempt to quantize all weights and activations of ProteinLMs. We observed that the typical uniform quantization method performs poorly on ESMFold, causing a significant drop in TM-Score when using 8-bit quantization. We conducted extensive quantization experiments, uncovering unique challenges associated with ESMFold, particularly highly asymmetric activation ranges before Layer Normalization, making representation difficult using low-bit fixed-point formats. To address these challenges, we propose a new PTQ method for ProteinLMs, utilizing piecewise linear quantization for asymmetric activation values to ensure accurate approximation. We demonstrated the effectiveness of our method in protein structure prediction tasks, demonstrating that ESMFold can be accurately quantized to low-bit widths without compromising accuracy. Additionally, we applied our method to the contact prediction task, showcasing its versatility. In summary, our study introduces an innovative PTQ method for ProteinLMs, addressing specific quantization challenges and potentially leading to the development of more efficient ProteinLMs with significant implications for various protein-related applications.
In this paper, conditional denoising diffusion probabilistic models (DDPMs) are proposed to enhance the data transmission and reconstruction over wireless channels. The underlying mechanism of DDPM is to decompose the data generation process over the so-called "denoising" steps. Inspired by this, the key idea is to leverage the generative prior of diffusion models in learning a "noisy-to-clean" transformation of the information signal to help enhance data reconstruction. The proposed scheme could be beneficial for communication scenarios in which a prior knowledge of the information content is available, e.g., in multimedia transmission. Hence, instead of employing complicated channel codes that reduce the information rate, one can exploit diffusion priors for reliable data reconstruction, especially under extreme channel conditions due to low signal-to-noise ratio (SNR), or hardware-impaired communications. The proposed DDPM-assisted receiver is tailored for the scenario of wireless image transmission using MNIST dataset. Our numerical results highlight the reconstruction performance of our scheme compared to the conventional digital communication, as well as the deep neural network (DNN)-based benchmark. It is also shown that more than 10 dB improvement in the reconstruction could be achieved in low SNR regimes, without the need to reduce the information rate for error correction.
This work addresses the need for efficient waste sorting strategies in Materials Recovery Facilities to minimize the environmental impact of rising waste. We propose resource-constrained semantic segmentation models for segmenting recyclable waste in industrial settings. Our goal is to develop models that fit within a 10MB memory constraint, suitable for edge applications with limited processing capacity. We perform the experiments on three networks: ICNet, BiSeNet (Xception39 backbone), and ENet. Given the aforementioned limitation, we implement quantization and pruning techniques on the broader nets, achieving positive results while marginally impacting the Mean IoU metric. Furthermore, we propose a combination of Focal and Lov\'asz loss that addresses the implicit class imbalance resulting in better performance compared with the Cross-entropy loss function.
We study high-probability convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. In the proposed scenario, the model is updated in an online fashion, as new information is observed, without storing any additional data. To combat the heavy-tailed noise, we consider a general framework of nonlinear stochastic gradient descent (SGD), providing several strong results. First, for non-convex costs and component-wise nonlinearities, we establish a convergence rate arbitrarily close to $\mathcal{O}\left(t^{-\frac{1}{4}}\right)$, whose exponent is independent of noise and problem parameters. Second, for strongly convex costs and component-wise nonlinearities, we establish a rate arbitrarily close to $\mathcal{O}\left(t^{-\frac{1}{2}}\right)$ for the weighted average of iterates, with exponent again independent of noise and problem parameters. Finally, for strongly convex costs and a broader class of nonlinearities, we establish convergence of the last iterate, with a rate $\mathcal{O}\left(t^{-\zeta} \right)$, where $\zeta \in (0,1)$ depends on problem parameters, noise and nonlinearity. As we show analytically and numerically, $\zeta$ can be used to inform the preferred choice of nonlinearity for given problem settings. Compared to state-of-the-art, who only consider clipping, require bounded noise moments of order $\eta \in (1,2]$, and establish convergence rates whose exponents go to zero as $\eta \rightarrow 1$, we provide high-probability guarantees for a much broader class of nonlinearities and symmetric density noise, with convergence rates whose exponents are bounded away from zero, even when the noise has finite first moment only. Moreover, in the case of strongly convex functions, we demonstrate analytically and numerically that clipping is not always the optimal nonlinearity, further underlining the value of our general framework.
The growing demand for Large Language Models (LLMs) in applications such as content generation, intelligent chatbots, and sentiment analysis poses considerable challenges for LLM service providers. To efficiently use GPU resources and boost throughput, batching multiple requests has emerged as a popular paradigm; to further speed up batching, LLM quantization techniques reduce memory consumption and increase computing capacity. However, prevalent quantization schemes (e.g., 8-bit weight-activation quantization) cannot fully leverage the capabilities of modern GPUs, such as 4-bit integer operators, resulting in sub-optimal performance. To maximize LLMs' serving throughput, we introduce Atom, a low-bit quantization method that achieves high throughput improvements with negligible accuracy loss. Atom significantly boosts serving throughput by using low-bit operators and considerably reduces memory consumption via low-bit quantization. It attains high accuracy by applying a novel mixed-precision and fine-grained quantization process. We evaluate Atom on 4-bit weight-activation quantization in the serving context. Atom improves end-to-end throughput (token/s) by up to $7.7\times$ compared to the FP16 and by $2.5\times$ compared to INT8 quantization, while maintaining the same latency target.
Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019.
In this paper, we present an efficient solution for weed classification in agriculture. We focus on optimizing model performance at inference while respecting the constraints of the agricultural domain. We propose a Quantized Deep Neural Network model that classifies a dataset of 9 weed classes using 8-bit integer (int8) quantization, a departure from standard 32-bit floating point (fp32) models. Recognizing the hardware resource limitations in agriculture, our model balances model size, inference time, and accuracy, aligning with practical requirements. We evaluate the approach on ResNet-50 and InceptionV3 architectures, comparing their performance against their int8 quantized versions. Transfer learning and fine-tuning are applied using the DeepWeeds dataset. The results show staggering model size and inference time reductions while maintaining accuracy in real-world production scenarios like Desktop, Mobile and Raspberry Pi. Our work sheds light on a promising direction for efficient AI in agriculture, holding potential for broader applications. Code: https://github.com/parikshit14/QNN-for-weed
Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that coverts the high-dimensional discrete features, such as user and item IDs, into low-dimensional continuous vectors and can enhance the recommendation performance. Applying embedding techniques captures complex entity relationships and has spurred substantial research. In this survey, we provide an overview of the recent literature on embedding techniques in recommender systems. This survey covers embedding methods like collaborative filtering, self-supervised learning, and graph-based techniques. Collaborative filtering generates embeddings capturing user-item preferences, excelling in sparse data. Self-supervised methods leverage contrastive or generative learning for various tasks. Graph-based techniques like node2vec exploit complex relationships in network-rich environments. Addressing the scalability challenges inherent to embedding methods, our survey delves into innovative directions within the field of recommendation systems. These directions aim to enhance performance and reduce computational complexity, paving the way for improved recommender systems. Among these innovative approaches, we will introduce Auto Machine Learning (AutoML), hash techniques, and quantization techniques in this survey. We discuss various architectures and techniques and highlight the challenges and future directions in these aspects. This survey aims to provide a comprehensive overview of the state-of-the-art in this rapidly evolving field and serve as a useful resource for researchers and practitioners working in the area of recommender systems.