Search Results for author:
Found 24 papers, 7 papers with code
Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models
As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning.
Follow Anything: Open-set detection, tracking, and following in real-time
We demonstrate FAn on a real-world robotic system (a micro aerial vehicle) and report its ability to seamlessly follow the objects of interest in a real-time control loop.
Dataset Distillation Meets Provable Subset Selection
Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields.
On the Size and Approximation Error of Distilled Sets
Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets?
AutoCoreset: An Automatic Practical Coreset Construction Framework
A coreset is a tiny weighted subset of an input set, that closely resembles the loss function, with respect to a certain set of queries.
Provable Data Subset Selection For Efficient Neural Network Training
In this paper, we introduce the first algorithm to construct coresets for \emph{RBFNNs}, i. e., small weighted subsets that approximate the loss of the input data on any radial basis function network and thus approximate any function defined by an \emph{RBFNN} on the larger input data.
ConceptFusion: Open-set Multimodal 3D Mapping
ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio.
Deep Learning on Home Drone: Searching for the Optimal Architecture
We suggest the first system that runs real-time semantic segmentation via deep learning on a weak micro-computer such as the Raspberry Pi Zero v2 (whose price was \$15) attached to a toy-drone.
Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions
Lately, coresets (provable data summarizations) were leveraged for pruning DNNs, adding the advantage of theoretical guarantees on the trade-off between the compression rate and the approximation error.
Obstacle Aware Sampling for Path Planning
While this approach is very simple, it can become costly when the obstacles are unknown, since samples hitting these obstacles are wasted.
Coresets for Data Discretization and Sine Wave Fitting
The goal (e. g., for anomaly detection) is to approximate the $n$ points received so far in $P$ by a single frequency $\sin$, e. g. $\min_{c\in C}cost(P, c)+\lambda(c)$, where $cost(P, c)=\sum_{i=1}^n \sin^2(\frac{2\pi}{N} p_ic)$, $C\subseteq [N]$ is a feasible set of solutions, and $\lambda$ is a given regularization function.
A Unified Approach to Coreset Learning
Our approach offers a new definition of coreset, which is a natural relaxation of the standard definition and aims at approximating the \emph{average} loss of the original data over the queries.
Introduction to Coresets: Approximated Mean
The survey may help guide new researchers unfamiliar with the field, and introduce them to the very basic foundations of coresets, through a simple, yet fundamental, problem.
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression.
Provably Approximated ICP
A harder version is the \emph{registration problem}, where the correspondence is unknown, and the minimum is also over all possible correspondence functions from $P$ to $Q$.
Provably Approximated Point Cloud Registration
A harder version is the registration problem, where the correspondence is unknown, and the minimum is also over all possible correspondence functions from P to Q. Algorithms such as the Iterative Closest Point (ICP) and its variants were suggested for these problems, but none yield a provable non-trivial approximation for the global optimum.
Deep Learning Meets Projective Clustering
Based on this approach, we provide a novel architecture that replaces the original embedding layer by a set of $k$ small layers that operate in parallel and are then recombined with a single fully-connected layer.
Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation
Here, $d$ is the number of the neurons in the layer, $n$ is the number in the next one, and $A_{k, 2}$ can be stored in $O((n+d)k)$ memory instead of $O(nd)$.
Coresets for Near-Convex Functions
Coreset is usually a small weighted subset of $n$ input points in $\mathbb{R}^d$, that provably approximates their loss function for a given set of queries (models, classifiers, etc.).
Faster PAC Learning and Smaller Coresets via Smoothed Analysis
PAC-learning usually aims to compute a small subset ($\varepsilon$-sample/net) from $n$ items, that provably approximates a given loss function for every query (model, classifier, hypothesis) from a given set of queries, up to an additive error $\varepsilon\in(0, 1)$.
Sets Clustering
The input to the \emph{sets-$k$-means} problem is an integer $k\geq 1$ and a set $\mathcal{P}=\{P_1,\cdots, P_n\}$ of sets in $\mathbb{R}^d$.
Introduction to Coresets: Accurate Coresets
A coreset (or core-set) of an input set is its small summation, such that solving a problem on the coreset as its input, provably yields the same result as solving the same problem on the original (full) set, for a given family of problems (models, classifiers, loss functions).
Tight Sensitivity Bounds For Smaller Coresets
With high probability, non-uniform sampling based on upper bounds on what is known as importance or sensitivity of each row in $A$ yields a coreset.
Fast and Accurate Least-Mean-Squares Solvers
Least-mean squares (LMS) solvers such as Linear / Ridge / Lasso-Regression, SVD and Elastic-Net not only solve fundamental machine learning problems, but are also the building blocks in a variety of other methods, such as decision trees and matrix factorizations.
