Search Results for author:
Found 8 papers, 4 papers with code
Proteus: Preserving Model Confidentiality during Graph Optimizations
Development of new DL models typically involves two parties: the model developers and performance optimizers.
Speeding up Fourier Neural Operators via Mixed Precision
In this work, we (i) profile memory and runtime for FNO with full and mixed-precision training, (ii) conduct a study on the numerical stability of mixed-precision training of FNO, and (iii) devise a training routine which substantially decreases training time and memory usage (up to 34%), with little or no reduction in accuracy, on the Navier-Stokes and Darcy flow equations.
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations
In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos.
AutoML for Climate Change: A Call to Action
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications.
NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
Zero-cost proxies (ZC proxies) are a recent architecture performance prediction technique aiming to significantly speed up algorithms for neural architecture search (NAS).
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
This makes the performance of NAS approaches in more diverse areas poorly understood.
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline.
Towards Deeper Generative Architectures for GANs using Dense connections
In this paper, we present the result of adopting skip connections and dense layers, previously used in image classification tasks, in the Fisher GAN implementation.
