Search Results for author:
Found 30 papers, 1 papers with code
From Selection to Generation: A Survey of LLM-based Active Learning
Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training.
PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks
Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL).
Annotation Efficiency: Identifying Hard Samples via Blocked Sparse Linear Bandits
This paper considers the problem of annotating datapoints using an expert with only a few annotation rounds in a label-scarce setting.
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
We consider the problem of high-dimensional heavy-tailed statistical estimation in the streaming setting, which is much harder than the traditional batch setting due to memory constraints.
FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction
To address both limitations, we propose FiRST, an algorithm that reduces inference latency by using layer-specific routers to select a subset of transformer layers adaptively for each input sequence - the prompt (during the prefill stage) decides which layers will be skipped during decoding.
Online Matrix Completion: A Collaborative Approach with Hott Items
In the regime where ${M},{N} >> {T}$, we propose two distinct computationally efficient algorithms for recommending items to users and analyze them under the benign \emph{hott items} assumption. 1) First, for ${S}=1$, under additional incoherence/smoothness assumptions on ${R}$, we propose the phased algorithm \textsc{PhasedClusterElim}.
Optimal Algorithms for Latent Bandits with Cluster Structure
Instead, we propose LATTICE (Latent bAndiTs via maTrIx ComplEtion) which allows exploitation of the latent cluster structure to provide the minimax optimal regret of $\widetilde{O}(\sqrt{(\mathsf{M}+\mathsf{N})\mathsf{T}})$, when the number of clusters is $\widetilde{O}(1)$.
Improved Support Recovery in Universal One-bit Compressed Sensing
A {\em universal} measurement matrix for 1bCS refers to one set of measurements that work for all sparse signals.
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
We then study the framework in the linear setting, where the problem reduces to that of estimating the sum of a rank-$r$ and a $k$-column sparse matrix using a small number of linear measurements.
Online Low Rank Matrix Completion
In each round, the algorithm recommends one item per user, for which it gets a (noisy) reward sampled from a low-rank user-item preference matrix.
Community Recovery in the Geometric Block Model
We show that a simple triangle-counting algorithm to detect communities in the geometric block model is near-optimal.
On Learning Mixture of Linear Regressions in the Non-Realizable Setting
In this paper we show that a version of the popular alternating minimization (AM) algorithm finds the best fit lines in a dataset even when a realizable model is not assumed, under some regularity conditions on the dataset and the initial points, and thereby provides a solution for the ERM.
Support Recovery in Mixture Models with Sparse Parameters
Sparsity of parameter vectors is a natural constraint in variety of settings, and support recovery is a major step towards parameter estimation.
Random Subgraph Detection Using Queries
Under the alternative, there is a subgraph on $k$ vertices with edge probability $p>q$.
Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians
Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory.
Support Recovery in Universal One-bit Compressed Sensing
With universality, it is known that $\tilde{\Theta}(k^2)$ 1bCS measurements are necessary and sufficient for support recovery (where $k$ denotes the sparsity).
Support Recovery of Sparse Signals from a Mixture of Linear Measurements
In this work, we study the number of measurements sufficient for recovering the supports of all the component vectors in a mixture in both these models.
Fuzzy Clustering with Similarity Queries
In particular, we provide algorithms for fuzzy clustering in this setting that asks $O(\mathsf{poly}(k)\log n)$ similarity queries and run with polynomial-time-complexity, where $n$ is the number of items.
Learning User Preferences in Non-Stationary Environments
One of the main surprising observations in our experiments is the fact our algorithm outperforms other static algorithms even when preferences do not change over time.
Recovery of sparse linear classifiers from mixture of responses
We look at a hitherto unstudied problem of query complexity upper bound of recovering all the hyperplanes, especially for the case when the hyperplanes are sparse.
Recovery of Sparse Signals from a Mixture of Linear Samples
Mixture of linear regressions is a popular learning theoretic model that is used widely to represent heterogeneous data.
Algebraic and Analytic Approaches for Parameter Learning in Mixture Models
Our second approach uses algebraic and combinatorial tools and applies to binomial mixtures with shared trial parameter $N$ and differing success parameters, as well as to mixtures of geometric distributions.
Sample Complexity of Learning Mixture of Sparse Linear Regressions
Ourtechniques are quite different from those in the previous work: for the noiselesscase, we rely on a property of sparse polynomials and for the noisy case, we providenew connections to learning Gaussian mixtures and use ideas from the theory of
Sample Complexity of Learning Mixtures of Sparse Linear Regressions
In the problem of learning mixtures of linear regressions, the goal is to learn a collection of signal vectors from a sequence of (possibly noisy) linear measurements, where each measurement is evaluated on an unknown signal drawn uniformly from this collection.
Same-Cluster Querying for Overlapping Clusters
In this paper, we look at the more practical scenario of overlapping clusters, and provide upper bounds (with algorithms) on the sufficient number of queries.
Semisupervised Clustering by Queries and Locally Encodable Source Coding
In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding.
High Dimensional Discrete Integration over the Hypergrid
Recently Ermon et al. (2013) pioneered a way to practically compute approximations to large scale counting or discrete integration problems by using random hashes.
Connectivity in Random Annulus Graphs and the Geometric Block Model
Our next contribution is in using the connectivity of random annulus graphs to provide necessary and sufficient conditions for efficient recovery of communities for {\em the geometric block model} (GBM).
Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding
In this paper, we show that a recently popular model of semisupervised clustering is equivalent to locally encodable source coding.
The Geometric Block Model
To capture the inherent geometric features of many community detection problems, we propose to use a new random graph model of communities that we call a Geometric Block Model.
