Training DNNs Resilient to Adversarial and Random Bit-Flips by Learning Quantization Ranges
#adversarial #quantization #dnns
'Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity', by Ali Kara, Naci Saldi, Serdar YĆ¼ksel.
http://jmlr.org/papers/v24/21-1457.html
#quantization #quantized #mdps
#quantization #quantized #mdps
Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices
#quantization #quantized #federated
PyTorch 2.0 has been released: https://pytorch.org/blog/pytorch-2.0-release/
Most of the new features are considered to be in a beta or prototype version.
#pytorch #compiler #quantization #tensor #cuda #Graviton3
Our lab will offer the two classes High Performance Computing and Efficient Machine Learning in the upcoming semester. New topics include BF16 support in SVE, recent features of PyTorch 2 and inference on mobile devices: https://scalable.uni-jena.de/teaching/2023/03/15/summer-semester.html
#fsujena #hpc #ml #bfloat16 #sve #arm #graviton3 #pytorch2 #quantization #snapdragon
#fsujena #hpc #ml #bfloat16 #SVE #arm #Graviton3 #pytorch2 #quantization #snapdragon
Image Compression with Product Quantized Masked Image Modeling
Alaaeldin El-Nouby, Matthew J. Muckley, Karen Ullrich, Ivan Laptev, Jakob Verbeek, Herve Jegou
#quantization #quantizer #Compression
Image Compression with Product Quantized Masked Image Modeling
#quantization #quantizer #Compression
#ExplainingMyResearch 2
But #symplectic and #Poisson structures appear in many contexts beyond classical mechanics: #Quantization, #stringtheory and the study of symmetries (via #Lie groups) come to mind.
#lie #stringtheory #quantization #poisson #symplectic #explainingmyresearch