Related papers: RangeGuard: Efficient, Bounded Approximate Error C…

We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that infinite-depth ResNets behave as if they were infinitely wide, regardless of their actual width. More…

State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operations. The range of magnitudes of many augmentation operations…

Previous research on selective protection for neural network components typically exploits only static vulnerability differences. Although these methods improve upon classical modular redundancy, they still incur substantial overhead for…

In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a lightweight device such as a mobile phone or edge device, and the remaining portion of the DNN is processed where more computing resources are…

Popular deep neural networks (DNNs) spend the majority of their execution time computing convolutions. The Winograd family of algorithms can greatly reduce the number of arithmetic operations required and is present in many DNN software…

Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity due to its capacity to reduce computational demands through…

Present-day Deep Reinforcement Learning (RL) systems show great promise towards building intelligent agents surpassing human-level performance. However, the computational complexity associated with the underlying deep neural networks (DNNs)…

Applications in the AI and HPC fields require much memory capacity, and the amount of energy consumed by main memory of server machines is ever increasing. Energy consumption of main memory can be greatly reduced by applying approximate…

In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of weights of the DNNs, such as the Frobenius and spectral…

Learning to predict solutions to real-valued combinatorial graph problems promises efficient approximations. As demonstrated based on the NP-hard edge clique cover number, recurrent neural networks (RNNs) are particularly suited for this…

Due to its high data density and longevity, DNA is considered a promising medium for satisfying ever-increasing data storage needs. However, the diversity of errors that occur in DNA sequences makes efficient error-correction a challenging…

Accurate approximation of scalar-valued functions from sample points is a key task in computational science. Recently, machine learning with Deep Neural Networks (DNNs) has emerged as a promising tool for scientific computing, with…

Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have shown external attacks such as adversarial examples that…

Large Language Models exhibit mode collapse, producing homogeneous outputs that fail to explore valid solution spaces. We present QD-LLM, a framework for parameter-efficient neuroevolution that evolves prompt embeddings, compact neural…

Deep Neural Networks (DNNs) are widely employed in safety-critical domains, where ensuring their reliability is essential. Triple Modular Redundancy (TMR) is an effective technique to enhance the reliability of DNNs in the presence of…

With the increasing deployment of deep neural networks (DNNs) in terrestrial and aerospace safety-critical applications, system reliability has emerged as a co-equal design metric alongside computational efficiency. Algorithm-based fault…

As neural networks make their way into safety-critical systems, where misbehavior can lead to catastrophes, there is a growing interest in certifying the equivalence of two structurally similar neural networks. For example, compression…

Training large language models (LLMs) efficiently while preserving model quality poses significant challenges, particularly with subbyte precision supported by state-of-the-art GPUs. Current mixed-precision training approaches either apply…

A key enabler of deploying convolutional neural networks on resource-constrained embedded systems is the binary neural network (BNN). BNNs save on memory and simplify computation by binarizing both features and weights. Unfortunately,…

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where…