Co-exploration of neural architectures and hardware accelerators has emerged as a promising approach to address computational cost problems, especially in low-profile systems. However, existing co-exploration methods based on reinforcement learning or evolutionary search suffer from substantial search costs. To address this, this work presents DANCE++, a differentiable approach towards the co-exploration of hardware and network architecture design. At the heart of DANCE++ is a differentiable evaluator network that models hardware metrics with a neural network, enabling accelerator design through backpropagation. DANCE++ significantly reduces search time and enhances accuracy and hardware cost metrics compared to traditional approaches. To further address real-world scenarios, this work embodies two important practical topics: hard constraints and data dependency. To meet the constraints such as frame rates or area budget, this work proposes a gradient manipulation algorithm that guides differentiable optimization to find hard-constrained solutions. Also to consider cases where training dataset is inaccessible, this work proposes to use data-free training methods in both co-exploration and training phases. To the best of our knowledge, DANCE++ is the first co-exploration method that targets these real-world challenges, supported by extensive experiments demonstrating its effectiveness.

Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for vision transformer (ViT) architectures, they fail to achieve efficacy in low-bit settings. Examining the existing methods, we observe that their synthetic data produce misaligned attention maps, while those of the real samples are highly aligned. From this observation, we find that aligning attention maps of synthetic data helps improve the overall performance of quantized ViTs. Motivated by this finding, we devise MimiQ, a novel DFQ method designed for ViTs that enhances inter-head attention similarity. First, we generate synthetic data by aligning head-wise attention outputs from each spatial query patch. Then, we align the attention maps of the quantized network to those of the full-precision teacher by applying head-wise structural attention distillation. The experimental results show that the proposed method significantly outperforms baselines, setting a new state-of-the-art for ViT-DFQ.

Low-bit floating-point (FP) formats, such as FP8, provide significant acceleration and memory savings in model training thanks to native hardware support on modern GPUs and NPUs. However, we analyze that FP8 quantization offers speedup primarily for large-dimensional matrix multiplications, while inherent quantization overheads diminish speedup when applied to low-rank adaptation (LoRA), which uses small-dimensional matrices for efficient fine-tuning of large language models (LLMs). To address this limitation, we propose FALQON, a novel framework that eliminates the quantization overhead from separate LoRA computational paths by directly merging LoRA adapters into an FP8-quantized backbone during fine-tuning. Furthermore, we reformulate the forward and backward computations for merged adapters to significantly reduce quantization overhead, and introduce a row-wise proxy update mechanism that efficiently integrates substantial updates into the quantized backbone. Experimental evaluations demonstrate that FALQON achieves approximately a 3$\times$ training speedup over existing quantized LoRA methods with a similar level of accuracy, providing a practical solution for efficient large-scale model fine-tuning. Moreover, FALQON’s end-to-end FP8 workflow removes the need for post-training quantization, facilitating efficient deployment. Code is available at https://github.com/iamkanghyunchoi/falqon.

Recent advances in adversarial robustness rely on an abundant set of training data, where using external or additional datasets has become a common setting. However, in real life, the training data is often kept private for security and privacy issues, while only the pretrained weight is available to the public. In such scenarios, existing methods that assume accessibility to the original data become inapplicable. Thus we investigate the pivotal problem of data-free adversarial robustness, where we try to achieve adversarial robustness without accessing any real data. Through a preliminary study, we highlight the severity of the problem by showing that robustness without the original dataset is difficult to achieve, even with similar domain datasets. To address this issue, we propose DataFreeShield, which tackles the problem from two perspectives: surrogate dataset generation and adversarial training using the generated data. Through extensive validation, we show that DataFreeShield outperforms baselines, demonstrating that the proposed method sets the first entirely data-free solution for the adversarial robustness problem.

Despite the fact that adversarial training provides an effective protection against adversarial attacks, it suffers from a huge computational overhead. To mitigate the overhead, we propose DBAC, a fast adversarial training with dynamic batch-level attack control. Based on a prior study where attack strength should gradually grow throughout the training, we control the number of samples attacked per batch for better throughput. Additionally, we collect samples from multiple batches to form a pseudo-batch and attack them simultaneously for higher GPU utilization. We implement DBAC using PyTorch to show its superior throughput with similar robust accuracy compared to the prior art.

Model quantization is considered as a promising method to greatly reduce the resource requirements of deep neural networks. To deal with the performance drop induced by quantization errors, a popular method is to use training data to fine-tune quantized networks. In real-world environments, however, such a method is frequently infeasible because training data is unavailable due to security, privacy, or confidentiality concerns. Zero-shot quantization addresses such problems, usually by taking information from the weights of a full-precision teacher network to compensate the performance drop of the quantized networks. In this paper, we first analyze the loss surface of state-of-the-art zero-shot quantization techniques and provide several findings. In contrast to usual knowledge distillation problems, zero-shot quantization often suffers from 1) the difficulty of optimizing multiple loss terms together, and 2) the poor generalization capability due to the use of synthetic samples. Furthermore, we observe that many weights fail to cross the rounding threshold during training the quantized networks even when it is necessary to do so for better performance. Based on the observations, we propose AIT, a simple yet powerful technique for zero-shot quantization, which addresses the aforementioned two problems in the following way: AIT i) uses a KL distance loss only without a cross-entropy loss, and ii) manipulates gradients to guarantee that a certain portion of weights are properly updated after crossing the rounding thresholds. Experiments show that AIT outperforms the performance of many existing methods by a great margin, taking over the overall state-of-the-art position in the field.

Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems. The large co-exploration space is often handled by adopting the idea of differentiable neural architecture search. However, despite the superior search efficiency of the differentiable co-exploration, it faces a critical challenge of not being able to systematically satisfy hard constraints such as frame rate. To handle the hard constraint problem of differentiable co-exploration, we propose HDX, which searches for hard-constrained solutions without compromising the global design objectives. By manipulating the gradients in the interest of the given hard constraint, high-quality solutions satisfying the constraint can be obtained.

This work presents DANCE, a differentiable approach towards the co-exploration of hardware accelerator and network architecture design. At the heart of DANCE is a differentiable evaluator network. By modeling the hardware evaluation software with a neural network, the relation between the accelerator design and the hardware metrics becomes differentiable, allowing the search to be performed with backpropagation. Compared to the naive existing approaches, our method performs co-exploration in a significantly shorter time, while achieving superior accuracy and hardware cost metrics.

Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to maintain the accuracy of the full-precision models, which is often infeasible in real-world scenarios for security and privacy issues.A popular approach to perform quantization without access to the original data is to use synthetically generated samples, based on batch-normalization statistics or adversarial learning.However, the drawback of such approaches is that they primarily rely on random noise input to the generator to attain diversity of the synthetic samples. We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries.To this end, we propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples.For the superposed embeddings to better reflect the original distribution, we also propose using an additional disentanglement mapping layer and extracting information from the full-precision model.The experimental results show that Qimera achieves state-of-the-art performances for various settings on data-free quantization. Code is available at https://github.com/iamkanghyunchoi/qimera.

Modern servers are actively deploying Solid-State Drives (SSDs) thanks to their high throughput and low latency. However, current server architects cannot achieve the full performance potential of commodity SSDs, as SSDs are complex devices designed for specific goals (e.g., latency, throughput, endurance, cost) with their internal mechanisms undisclosed to users. In this article, we propose SSDcheck , a novel SSD performance model to extract various internal mechanisms and predict the latency of next access to commodity black-box SSDs. We identify key performance-critical features (e.g., garbage collection, write buffering) and find their parameters (i.e., size, threshold) from each SSD by using our novel diagnosis code snippets. Then, SSDcheck constructs a performance model for a target SSD and dynamically manages the model to predict the latency of the next access. In addition, SSDcheck extracts and provides other useful internal mechanisms (e.g., fetch unit in multi-queue SSDs, background tasks triggering idle-time interval) for the storage system to fully exploit SSDs. By using those useful features and the performance model, we propose multiple practical use cases. Our evaluations show that SSDcheck’s performance model is highly accurate, and proposed use cases achieve significant performance improvement in various scenarios.