Search Results for author:
Found 36 papers, 5 papers with code
Explainable k-Means and k-Medians Clustering
In terms of negative results, we show that popular top-down decision tree algorithms may lead to clusterings with arbitrarily large cost, and we prove that any explainable clustering must incur an \Omega(\log k) approximation compared to the optimal clustering.
Online nearest neighbor classification
We study an instance of online non-parametric classification in the realizable setting.
Active learning using region-based sampling
We present a general-purpose active learning scheme for data in metric spaces.
Data-Copying in Generative Models: A Formal Framework
There has been some recent interest in detecting and addressing memorization of training data by deep neural networks.
Streaming Encoding Algorithms for Scalable Hyperdimensional Computing
Hyperdimensional computing (HDC) is a paradigm for data representation and learning originating in computational neuroscience.
Convergence of online $k$-means
We prove asymptotic convergence for a general class of $k$-means algorithms performed over streaming data from a distribution: the centers asymptotically converge to the set of stationary points of the $k$-means cost function.
Framework for Evaluating Faithfulness of Local Explanations
We study the faithfulness of an explanation system to the underlying prediction model.
Algorithmic insights on continual learning from fruit flies
We discovered a two layer neural circuit in the fruit fly olfactory system that addresses this challenge by uniquely combining sparse coding and associative learning.
Online $k$-means Clustering on Arbitrary Data Streams
We propose a data parameter, $\Lambda(X)$, such that for any algorithm maintaining $O(k\text{poly}(\log n))$ centers at time $n$, there exists a data stream $X$ for which a loss of $\Omega(\Lambda(X))$ is inevitable.
A Theoretical Perspective on Hyperdimensional Computing
Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining high-dimensional, low-precision, distributed representations of data.
Expressivity of expand-and-sparsify representations
The linear functions can be specified explicitly and are easy to learn, and we give bounds on how large $m$ needs to be as a function of the input dimension $d$ and the smoothness of the target function.
A Non-Parametric Test to Detect Data-Copying in Generative Models
Detecting overfitting in generative models is an important challenge in machine learning.
Robust Learning from Discriminative Feature Feedback
We show how such errors can be handled algorithmically, in both an adversarial and a stochastic setting.
Explainable $k$-Means and $k$-Medians Clustering
In terms of negative results, we show, first, that popular top-down decision tree algorithms may lead to clusterings with arbitrarily large cost, and second, that any tree-induced clustering must in general incur an $\Omega(\log k)$ approximation factor compared to the optimal clustering.
Interactive Topic Modeling with Anchor Words
The formalism of anchor words has enabled the development of fast topic modeling algorithms with provable guarantees.
An adaptive nearest neighbor rule for classification
We introduce a variant of the $k$-nearest neighbor classifier in which $k$ is chosen adaptively for each query, rather than supplied as a parameter.
What relations are reliably embeddable in Euclidean space?
We consider the problem of embedding a relation, represented as a directed graph, into Euclidean space.
Learning from discriminative feature feedback
We consider the problem of learning a multi-class classifier from labels as well as simple explanations that we call "discriminative features".
Interactive Structure Learning with Structural Query-by-Committee
In this work, we introduce interactive structure learning, a framework that unifies many different interactive learning tasks.
Structural query-by-committee
In this work, we describe a framework that unifies many different interactive learning tasks.
Comparison Based Learning from Weak Oracles
More specifically, we aim at devising efficient algorithms to locate a target object in a database equipped with a dissimilarity metric via invocation of the weak comparison oracle.
Learning from partial correction
We introduce a new model of interactive learning in which an expert examines the predictions of a learner and partially fixes them if they are wrong.
Diameter-Based Active Learning
To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index.
An algorithm for L1 nearest neighbor search via monotonic embedding
Fast algorithms for nearest neighbor (NN) search have in large part focused on L2 distance.
Interactive Bayesian Hierarchical Clustering
Clustering is a powerful tool in data analysis, but it is often difficult to find a grouping that aligns with a user's needs.
A cost function for similarity-based hierarchical clustering
The development of algorithms for hierarchical clustering has been hampered by a shortage of precise objective functions.
The Fast Convergence of Incremental PCA
We consider a situation in which we see samples in $\mathbb{R}^d$ drawn i. i. d.
Optimal rates for k-NN density and mode estimation
We present two related contributions of independent interest: (1) high-probability finite sample rates for $k$-NN density estimation, and (2) practical mode estimators -- based on $k$-NN -- which attain minimax-optimal rates under surprisingly general distributional conditions.
Rates of Convergence for Nearest Neighbor Classification
Nearest neighbor methods are a popular class of nonparametric estimators with several desirable properties, such as adaptivity to different distance scales in different regions of space.
Incremental Clustering: The Case for Extra Clusters
The explosion in the amount of data available for analysis often necessitates a transition from batch to incremental clustering methods, which process one element at a time and typically store only a small subset of the data.
Consistent procedures for cluster tree estimation and pruning
For a density $f$ on ${\mathbb R}^d$, a {\it high-density cluster} is any connected component of $\{x: f(x) \geq \lambda\}$, for some $\lambda > 0$.
Moment-based Uniform Deviation Bounds for k-means and Friends
Suppose $k$ centers are fit to $m$ points by heuristically minimizing the $k$-means cost; what is the corresponding fit over the source distribution?
Moment-based Uniform Deviation Bounds for $k$-means and Friends
Suppose $k$ centers are fit to $m$ points by heuristically minimizing the $k$-means cost; what is the corresponding fit over the source distribution?
Rates of convergence for the cluster tree
For a density f on R^d, a high-density cluster is any connected component of {x: f(x) >= c}, for some c > 0.
A learning framework for nearest neighbor search
Can we leverage learning techniques to build a fast nearest-neighbor (NN) retrieval data structure?
Learning the structure of manifolds using random projections
We present a simple variant of the k-d tree which automatically adapts to intrinsic low dimensional structure in data.
