Memory Efficient Mixed-Precision Optimizers von Lewandowski, Basile, Kosson, Atli

Volltext bestellen

Multiplication-Free Transformer Training via Piecewise Affine Operations von Kosson, Atli, Jaggi, Martin

Volltext bestellen

Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training von Kosson, Atli, Messmer, Bettina, Jaggi, Martin

Volltext bestellen

Ghost Noise for Regularizing Deep Neural Networks von Kosson, Atli, Fan, Dongyang, Jaggi, Martin

Volltext bestellen

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks von Kosson, Atli, Messmer, Bettina, Jaggi, Martin

Volltext bestellen

Multiplication-Free Transformer Training via Piecewise Affine Operations von Kosson, Atli, Jaggi, Martin

Volltext

Memory Efficient Mixed-Precision Optimizers von Lewandowski, Basile, Kosson, Atli

Volltext

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations von Hägele, Alexander, Bakouch, Elie, Kosson, Atli, Allal, Loubna Ben, Von Werra, Leandro, Jaggi, Martin

Volltext bestellen

Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training von Kosson, Atli, Messmer, Bettina, Jaggi, Martin

Volltext

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks von Kosson, Atli, Messmer, Bettina, Jaggi, Martin

Volltext

Ghost Noise for Regularizing Deep Neural Networks von Kosson, Atli, Fan, Dongyang, Jaggi, Martin

Volltext

Adaptive Braking for Mitigating Gradient Delay von Venigalla, Abhinav, Kosson, Atli, Chiley, Vitaliy, Köster, Urs

Volltext bestellen

Pipelined Backpropagation at Scale: Training Large Models without Batches von Kosson, Atli, Chiley, Vitaliy, Venigalla, Abhinav, Hestness, Joel, Köster, Urs

Volltext bestellen

SYSTEM AND METHOD FOR BRAINWAVE STIMULATION USING ALTERED NATURAL STIMULI von KOSSON, Atli, SVEINBJARNARSON, Bjarki Freyr, HOSKULDSSON, Sveinbjorn

Volltext bestellen

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations von Hägele, Alexander, Bakouch, Elie, Kosson, Atli, Loubna Ben Allal, Leandro Von Werra, Jaggi, Martin

Volltext

SYSTEM FOR BRAINWAVE STIMULATION USING ALTERED NATURAL STIMULI von KOSSON, Atli, SVEINBJARNARSON, Bjarki Freyr, HOSKULDSSON, Sveinbjorn

Volltext bestellen

Pipelined Backpropagation at Scale: Training Large Models without Batches von Kosson, Atli, Chiley, Vitaliy, Venigalla, Abhinav, Hestness, Joel, Köster, Urs

Volltext

Online Normalization for Training Neural Networks von Chiley, Vitaliy, Sharapov, Ilya, Kosson, Atli, Koster, Urs, Reece, Ryan, de la Fuente, Sofia Samaniego, Subbiah, Vishal, James, Michael

Volltext bestellen

Adaptive Braking for Mitigating Gradient Delay von Venigalla, Abhinav, Kosson, Atli, Chiley, Vitaliy, Köster, Urs

Volltext

Online Normalization for Training Neural Networks von Chiley, Vitaliy, Sharapov, Ilya, Kosson, Atli, Koster, Urs, Reece, Ryan, Sofia Samaniego de la Fuente, Subbiah, Vishal, James, Michael

Volltext