Search Results for author:
Found 14 papers, 6 papers with code
Causal Fourier Analysis on Directed Acyclic Graphs and Posets
DAGs are the common model to capture causal relationships between data and our framework is causal in that shift, convolution, and Fourier transform are computed only from predecessors in the DAG.
PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations
Formal verification of neural networks is critical for their safe adoption in real-world applications.
Faster Training of Word Embeddings
Word embeddings have gained increasing popularity in the recent years due to the Word2vec library and its extension fastText that uses subword information.
Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases
Many applications of machine learning on discrete domains, such as learning preference functions in recommender systems or auctions, can be reduced to estimating a set function that is sparse in the Fourier domain.
Scaling Polyhedral Neural Network Verification on GPUs
GPUPoly scales to large networks: for example, it can prove the robustness of a 1M neuron, 34-layer deep residual network in approximately 34. 5 ms. We believe GPUPoly is a promising step towards practical verification of real-world neural networks.
Digraph Signal Processing with Generalized Boundary Conditions
Furthermore, the Fourier transform in this case is now obtained from the Jordan decomposition, which may not be computable at all for large graphs.
Discrete Signal Processing with Set Functions
Set functions are functions (or signals) indexed by the powerset (set of all subsets) of a finite set N. They are fundamental and ubiquitous in many application domains and have been used, for example, to formally describe or quantify loss functions for semantic image segmentation, the informativeness of sensors in sensor networks the utility of sets of items in recommender systems, cooperative games in game theory, or bidders in combinatorial auctions.
Beyond the Single Neuron Convex Barrier for Neural Network Certification
We propose a new parametric framework, called k-ReLU, for computing precise and scalable convex relaxations used to certify neural networks.
Powerset Convolutional Neural Networks
We present a novel class of convolutional neural networks (CNNs) for set functions, i. e., data indexed with the powerset of a finite set.
On Linear Learning with Manycore Processors
A new generation of manycore processors is on the rise that offers dozens and more cores on a chip and, in a sense, fuses host processor and accelerator.
Robustness Certification with Refinement
We present a novel approach for verification of neural networks which combines scalable over-approximation methods with precise (mixed integer) linear programming.
Fast and Effective Robustness Certification
We present a new method and system, called DeepZ, for certifying neural network robustness based on abstract interpretation.
Compressive Sensing Using Iterative Hard Thresholding with Low Precision Data Representation: Theory and Applications
Modern scientific instruments produce vast amounts of data, which can overwhelm the processing ability of computer systems.
Distributed Optimization With Local Domains: Applications in MPC and Network Flows
Our contribution is a communication-efficient distributed algorithm that finds a vector $x^\star$ minimizing the sum of all the functions.
Optimization and Control Information Theory Information Theory
