116 citations · 1.1k across the 96 of their papers we have counts for
5 papers · 1 filter
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
Pratik Chaudhari, Anna Choromanska, Stefano Soatto +6
This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema…
Information Dropout: Learning Optimal Representations Through Noisy Computation
Alessandro Achille, Stefano Soatto
The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We…
ShapeFit and ShapeKick for Robust, Scalable Structure from Motion
Thomas Goldstein, Paul Hand, Choongbum Lee +2
We introduce a new method for location recovery from pair-wise directions that leverages an efficient convex program that comes with exact recovery guarantees, even in the presence…
Visual-Inertial-Semantic Scene Representation for 3-D Object Detection
Jingming Dong, Xiaohan Fei, Stefano Soatto
We describe a system to detect objects in three-dimensional space using video and inertial sensors (accelerometer and gyrometer), ubiquitous in modern mobile platforms from phones…
A Theory of Local Matching: SIFT and Beyond
Hossein Mobahi, Stefano Soatto
Why has SIFT been so successful? Why its extension, DSP-SIFT, can further improve SIFT? Is there a theory that can explain both? How can such theory benefit real applications? Can…