Search Results for author:
Found 23 papers, 3 papers with code
On Mergable Coresets for Polytope Distance
We show that a constant-size constant-error coreset for polytope distance is simple to maintain under merges of coresets.
Understanding the Effect of the Long Tail on Neural Network Compression
E. g., it has been shown that mismatches between the full and compressed models can be biased towards under-represented classes.
Online Learning and Bandits with Queried Hints
For stochastic MAB, we also consider a stronger model where a probe reveals the reward values of the probed arms, and show that in this case, $k=3$ probes suffice to achieve parameter-independent constant regret, $O(n^2)$.
Logarithmic Regret from Sublinear Hints
We consider the online linear optimization problem, where at every step the algorithm plays a point $x_t$ in the unit ball, and suffers loss $\langle c_t, x_t\rangle$ for some cost vector $c_t$ that is then revealed to the algorithm.
Going Beyond Classification Accuracy Metrics in Model Compression
With the rise in edge-computing devices, there has been an increasing demand to deploy energy and resource-efficient models.
Online MAP Inference of Determinantal Point Processes
In this paper, we provide an efficient approximation algorithm for finding the most likelihood configuration (MAP) of size $k$ for Determinantal Point Processes (DPP) in the online setting where the data points arrive in an arbitrary order and the algorithm cannot discard the selected elements from its local memory.
Adaptive Probing Policies for Shortest Path Routing
Inspired by traffic routing applications, we consider the problem of finding the shortest path from a source $s$ to a destination $t$ in a graph, when the lengths of the edges are unknown.
Online Linear Optimization with Many Hints
We study an online linear optimization (OLO) problem in which the learner is provided access to $K$ "hint" vectors in each round prior to making a decision.
Fair clustering via equitable group representations
A core principle in most clustering problems is that a cluster center should be representative of the cluster it represents, by being "close" to the points associated with it.
Online Learning with Imperfect Hints
We consider a variant of the classical online linear optimization problem in which at every step, the online player receives a "hint" vector before choosing the action for that round.
On Distributed Averaging for Stochastic k-PCA
The server performs an aggregation and computes the desired eigenvalues and vectors.
Greedy Sampling for Approximate Clustering in the Presence of Outliers
One the one hand, they possess good theoretical approximation guarantees, and on the other, they are fast and easy to implement.
Approximate Guarantees for Dictionary Learning
The problem is formalized as factorizing a matrix $X (d \times n)$ (whose columns are the signals) as $X = AY$, where $A$ has a prescribed number $m$ of columns (typically $m \ll n$), and $Y$ has columns that are $k$-sparse (typically $k \ll d$).
Smoothed Analysis in Unsupervised Learning via Decoupling
Smoothed analysis is a powerful paradigm in overcoming worst-case intractability in unsupervised learning and high-dimensional data analysis.
Distributed Clustering via LSH Based Data Partitioning
Given the importance of clustering in the analysisof large scale data, distributed algorithms for formulations such as k-means, k-median, etc.
Linear Relaxations for Finding Diverse Elements in Metric Spaces
We first study the approximation quality of the algorithm by comparing with the LP objective.
On Binary Embedding using Circulant Matrices
To address this problem, we propose Circulant Binary Embedding (CBE) which generates binary codes by projecting the data with a circulant matrix.
Sparse Solutions to Nonnegative Linear Systems and Applications
For learning a mixture of $k$ axis-aligned Gaussians in $d$ dimensions, we give an algorithm that outputs a mixture of $O(k/\epsilon^3)$ Gaussians that is $\epsilon$-close in statistical distance to the true distribution, without any separation assumptions.
Distributed Balanced Clustering via Mapping Coresets
Large-scale clustering of data points in metric spaces is an important problem in mining big data sets.
More Algorithms for Provable Dictionary Learning
In dictionary learning, also known as sparse coding, the algorithm is given samples of the form $y = Ax$ where $x\in \mathbb{R}^m$ is an unknown random sparse vector and $A$ is an unknown dictionary matrix in $\mathbb{R}^{n\times m}$ (usually $m > n$, which is the overcomplete case).
Smoothed Analysis of Tensor Decompositions
We introduce a smoothed analysis model for studying these questions and develop an efficient algorithm for tensor decomposition in the highly overcomplete case (rank polynomial in the dimension).
Provable Bounds for Learning Some Deep Representations
The analysis of the algorithm reveals interesting structure of neural networks with random edge weights.
Uniqueness of Tensor Decompositions with Applications to Polynomial Identifiability
We give a robust version of the celebrated result of Kruskal on the uniqueness of tensor decompositions: we prove that given a tensor whose decomposition satisfies a robust form of Kruskal's rank condition, it is possible to approximately recover the decomposition if the tensor is known up to a sufficiently small (inverse polynomial) error.
