Search Results for author:
Found 10 papers, 4 papers with code
Machine Unlearning for Image-to-Image Generative Models
This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models.
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
Predictive multiplicity refers to the phenomenon in which classification tasks may admit multiple competing models that achieve almost-equally-optimal performance, yet generate conflicting outputs for individual samples.
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models
The rapid growth of machine learning has spurred legislative initiatives such as ``the Right to be Forgotten,'' allowing users to request data removal.
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities
Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process.
TIPS: Topologically Important Path Sampling for Anytime Neural Networks
Anytime neural networks (AnytimeNNs) are a promising solution to adaptively adjust the model complexity at runtime under various hardware resource constraints.
ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients
Based on this theoretical analysis, we propose a new zero-shot proxy, ZiCo, the first proxy that works consistently better than #Params.
Efficient On-device Training via Gradient Filtering
Despite its importance for federated learning, continuous learning and many other applications, on-device training remains an open problem for EdgeAI.
FLASH: Fast Neural Architecture Search with Hardware Optimization
This paper proposes FLASH, a very fast NAS methodology that co-optimizes the DNN accuracy and performance on a real hardware platform.
On the relationship between topology and gradient propagation in deep networks
(ii) Can certain topological characteristics of deep networks indicate a priori (i. e., without training) which models, with a different number of parameters/FLOPS/layers, achieve a similar accuracy?
How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?
In this paper, we reveal that the topology of the concatenation-type skip connections is closely related to the gradient propagation which, in turn, enables a predictable behavior of DNNs' test performance.
