23 citations · 58 across the 11 of their papers we have counts for
11 papers
Federated Lightweight Fine-Tuning
Radhakrishna Achanta, Will Reed
Federated fine-tuning is bottlenecked by communication: FedAvg and pseudo-gradient schemes transmit a payload that scales with the model, and gradient compression shrinks it by onl…
TallyTrain: Communication-Efficient Federated Distillation
Radhakrishna Achanta, Will Reed
Federated learning is bandwidth-bound on two orthogonal axes: model size, which limits how often parameter-averaging methods can afford to merge, and class count, which makes per-p…
Exploiting the Signal-Leak Bias in Diffusion Models
Martin Nicolas Everaert, Athanasios Fitsios, Marco Bocchio +3
There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepa…
What You See is What You Classify: Black Box Attributions
Steven Stalder, Nathanaël Perraudin, Radhakrishna Achanta +2
An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, d…
Uncertainty Surrogates for Deep Learning
Radhakrishna Achanta, Natasa Tagasovska
In this paper we introduce a novel way of estimating prediction uncertainty in deep networks through the use of uncertainty surrogates. These surrogates are features of the penulti…
Image Obfuscation for Privacy-Preserving Machine Learning
Mathilde Raynal, Radhakrishna Achanta, Mathias Humbert
Privacy becomes a crucial issue when outsourcing the training of machine learning (ML) models to cloud-based platforms offering machine-learning services. While solutions based on…