Bob Pepin

According to our database, Bob Pepin authored at least 7 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks.

Jonathan Wenshøj, Tong Chen, Bob Pepin, Raghavendra Selvan

CoRR, December, 2025

Oscillations Make Neural Networks Robust to Quantization.

Jonathan Wenshøj, Bob Pepin, Raghavendra Selvan

Trans. Mach. Learn. Res., 2025

PePR: Performance Per Resource Unit as a Metric to Promote Small-scale Deep Learning.

Raghavendra Selvan, Bob Pepin, Christian Igel, Gabrielle Samuel, Erik B. Dam

Proceedings of the Northern Lights Deep Learning Conference, 2025

2024

The Harmonic Indel Distance.

Bob Pepin

Trans. Mach. Learn. Res., 2024

When Can Memorization Improve Fairness?

Bob Pepin, Christian Igel, Raghavendra Selvan

CoRR, 2024

Equity through Access: A Case for Small-scale Deep Learning.

Raghavendra Selvan, Bob Pepin, Christian Igel, Gabrielle Samuel, Erik B. Dam

CoRR, 2024

2020

The Harmonic Edit Distance.

Bob Pepin

CoRR, 2020