Post-Training Statistical Calibration for Higher Activation Sparsity

We present Statistical Calibrated Activation Pruning (SCAP), a post-training activation pruning framework that (1) generalizes sparsification by input activations of Fully-Connected layers for generic and flexible application across Transformers, and (2) features a simple Mode-Centering technique to pre-calibrate activation distributions for maximizing post-training sparsity. Our results demonstrate robust Pareto efficiency compared to prior methods, translating to a 1.5x additional LLM decoding speedup against CATS at iso model quality. SCAP effectiveness is empirically verified across a wide range of models, including recent Transformer Decoders, MoE, Mamba2, Encoding Transformer, and pre-quantized models, highlighting its practicality and scalability. The code is available at: https://github.com/IntelLabs/SCAP.

SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models

Large pre-trained models (LPMs), such as large language models, have become ubiquitous and are employed in many applications. These models are often adapted to a desired domain or downstream task through a fine-tuning stage. This paper proposes SQFT, an end-to-end solution for low-precision sparse parameter-efficient fine-tuning of LPMs, allowing for effective model manipulation in resource-constrained environments. Additionally, an innovative strategy enables the merging of sparse weights with low-rank adapters without losing sparsity and accuracy, overcoming the limitations of previous approaches. SQFT also addresses the challenge of having quantized weights and adapters with different numerical precisions, enabling merging in the desired numerical format without sacrificing accuracy. Multiple adaptation scenarios, models, and comprehensive sparsity levels demonstrate the effectiveness of SQFT. Models and code are available at https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.

Shears: Unstructured Sparsity with Neural Low-rank Adapter Search

Recently, several approaches successfully demonstrated that weight-sharing Neural Architecture Search (NAS) can effectively explore a search space of elastic low-rank adapters (LoRA), allowing the parameter-efficient fine-tuning (PEFT) and compression of large language models. In this paper, we introduce a novel approach called Shears, demonstrating how the integration of cost-effective sparsity and a proposed Neural Low-rank adapter Search (NLS) algorithm can further improve the efficiency of PEFT approaches. Results demonstrate the benefits of Shears compared to other methods, reaching high sparsity levels while improving or with little drop in accuracy, utilizing a single GPU for a pair of hours.

Mem-Rec: Memory Efficient Recommendation System using Alternative Representation

Deep learning-based recommendation systems (e.g., DLRMs) are widely used AI models to provide high-quality personalized recommendations. Training data used for modern recommendation systems commonly includes categorical features taking on tens-of-millions of possible distinct values. These categorical tokens are typically assigned learned vector representations, that are stored in large embedding tables, on the order of 100s of GB. Storing and accessing these tables represent a substantial burden in commercial deployments. Our work proposes MEM-REC, a novel alternative representation approach for embedding tables. MEM-REC leverages bloom filters and hashing methods to encode categorical features using two cache-friendly embedding tables. The first table (token embedding) contains raw embeddings (i.e. learned vector representation), and the second table (weight embedding), which is much smaller, contains weights to scale these raw embeddings to provide better discriminative capability to each data point. We provide a detailed architecture, design and analysis of MEM-REC addressing trade-offs in accuracy and computation requirements, in comparison with state-of-the-art techniques. We show that MEM-REC can not only maintain the recommendation quality and significantly reduce the memory footprint for commercial scale recommendation models but can also improve the embedding latency. In particular, based on our results, MEM-REC compresses the MLPerf CriteoTB benchmark DLRM model size by 2900x and performs up to 3.4x faster embeddings while achieving the same AUC as that of the full uncompressed model.

Streaming Encoding Algorithms for Scalable Hyperdimensional Computing

Hyperdimensional computing (HDC) is a paradigm for data representation and learning originating in computational neuroscience. HDC represents data as high-dimensional, low-precision vectors which can be used for a variety of information processing tasks like learning or recall. The mapping to high-dimensional space is a fundamental problem in HDC, and existing methods encounter scalability issues when the input data itself is high-dimensional. In this work, we explore a family of streaming encoding techniques based on hashing. We show formally that these methods enjoy comparable guarantees on performance for learning applications while being substantially more efficient than existing alternatives. We validate these results experimentally on a popular high-dimensional classification problem and show that our approach easily scales to very large data sets.

Evolving Zero Cost Proxies For Neural Architecture Scoring

Neural Architecture Search (NAS) has significantly improved productivity in the design and deployment of neural networks (NN). As NAS typically evaluates multiple models by training them partially or completely, the improved productivity comes at the cost of significant carbon footprint. To alleviate this expensive training routine, zero-shot/cost proxies analyze an NN at initialization to generate a score, which correlates highly with its true accuracy. Zero-cost proxies are currently designed by experts conducting multiple cycles of empirical testing on possible algorithms, data-sets, and neural architecture design spaces. This lowers productivity and is an unsustainable approach towards zero-cost proxy design as deep learning use-cases diversify in nature. Additionally, existing zero-cost proxies fail to generalize across neural architecture design spaces. In this paper, we propose a genetic programming framework to automate the discovery of zero-cost proxies for neural architecture scoring. Our methodology efficiently discovers an interpretable and generalizable zero-cost proxy that gives state of the art score-accuracy correlation on all data-sets and search spaces of NASBench-201 and Network Design Spaces (NDS). We believe that this research indicates a promising direction towards automatically discovering zero-cost proxies that can work across network architecture design spaces, data-sets, and tasks.

Enabling NAS with Automated Super-Network Generation

Recent Neural Architecture Search (NAS) solutions have produced impressive results training super-networks and then deriving subnetworks, a.k.a. child models that outperform expert-crafted models from a pre-defined search space. Efficient and robust subnetworks can be selected for resource-constrained edge devices, allowing them to perform well in the wild. However, constructing super-networks for arbitrary architectures is still a challenge that often prevents the adoption of these approaches. To address this challenge, we present BootstrapNAS, a software framework for automatic generation of super-networks for NAS. BootstrapNAS takes a pre-trained model from a popular architecture, e.g., ResNet- 50, or from a valid custom design, and automatically creates a super-network out of it, then uses state-of-the-art NAS techniques to train the super-network, resulting in subnetworks that significantly outperform the given pre-trained model. We demonstrate the solution by generating super-networks from arbitrary model repositories and make available the resulting super-networks for reproducibility of the results.

RHNAS: Realizable Hardware and Neural Architecture Search

The rapidly evolving field of Artificial Intelligence necessitates automated approaches to co-design neural network architecture and neural accelerators to maximize system efficiency and address productivity challenges. To enable joint optimization of this vast space, there has been growing interest in differentiable NN-HW co-design. Fully differentiable co-design has reduced the resource requirements for discovering optimized NN-HW configurations, but fail to adapt to general hardware accelerator search spaces. This is due to the existence of non-synthesizable (invalid) designs in the search space of many hardware accelerators. To enable efficient and realizable co-design of configurable hardware accelerators with arbitrary neural network search spaces, we introduce RHNAS. RHNAS is a method that combines reinforcement learning for hardware optimization with differentiable neural architecture search. RHNAS discovers realizable NN-HW designs with 1.84x lower latency and 1.86x lower energy-delay product (EDP) on ImageNet and 2.81x lower latency and 3.30x lower EDP on CIFAR-10 over the default hardware accelerator design.

Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization

Mixed-precision quantization is a powerful tool to enable memory and compute savings of neural network workloads by deploying different sets of bit-width precisions on separate compute operations. Recent research has shown significant progress in applying mixed-precision quantization techniques to reduce the memory footprint of various workloads, while also preserving task performance. Prior work, however, has often ignored additional objectives, such as bit-operations, that are important for deployment of workloads on hardware. Here we present a flexible and scalable framework for automated mixed-precision quantization that optimizes multiple objectives. Our framework relies on Neuroevolution-Enhanced Multi-Objective Optimization (NEMO), a novel search method, to find Pareto optimal mixed-precision configurations for memory and bit-operations objectives. Within NEMO, a population is divided into structurally distinct sub-populations (species) which jointly form the Pareto frontier of solutions for the multi-objective problem. At each generation, species are re-sized in proportion to the goodness of their contribution to the Pareto frontier. This allows NEMO to leverage established search techniques and neuroevolution methods to continually improve the goodness of the Pareto frontier. In our experiments we apply a graph-based representation to describe the underlying workload, enabling us to deploy graph neural networks trained by NEMO to find Pareto optimal configurations for various workloads trained on ImageNet. Compared to the state-of-the-art, we achieve competitive results on memory compression and superior results for compute compression for MobileNet-V2, ResNet50 and ResNeXt-101-32x8d. A deeper analysis of the results obtained by NEMO also shows that both the graph representation and the species-based approach are critical in finding effective configurations for all workloads.