Search Results for author:
Found 20 papers, 0 papers with code
Self-Similar Epochs: Value in Arrangement
Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples.
Clustering Small Samples with Quality Guarantees: Adaptivity with One2all pps
At the core of our design is the {\em one2all} construction of multi-objective probability-proportional-to-size (pps) samples: Given a set $M$ of centroids and $\alpha \geq 1$, one2all efficiently assigns probabilities to points so that the clustering cost of {\em each} $Q$ with cost $V(Q) \geq V(M)/\alpha$ can be estimated well from a sample of size $O(\alpha |M|\epsilon^{-2})$.
Bootstrapped Graph Diffusions: Exposing the Power of Nonlinearity
Classic methods capture the graph structure through some underlying diffusion process that propagates through the graph edges.
Semi-Supervised Learning on Graphs through Reach and Distance Diffusion
Inspired by the success of social influence as an alternative to spectral centrality such as Page Rank, we explore SSL with our kernels and develop highly scalable algorithms for parameter setting, label learning, and sampling.
Average Distance Queries through Weighted Samples in Graphs and Metric Spaces: High Scalability with Tight Statistical Guarantees
The estimate is based on a weighted sample of $O(\epsilon^{-2})$ pairs of points, which is computed using $O(n)$ distance computations.
LSH Microbatches for Stochastic Gradients: Value in Rearrangement
We make a principled argument for the properties of our arrangements that accelerate the training and present efficient algorithms to generate microbatches that respect the marginal distribution of training examples.
All-Distances Sketches, Revisited: HIP Estimators for Massive Graphs Analysis
We present the Historic Inverse Probability (HIP) estimators which are applied to the ADS of a node to estimate a large natural class of statistics.
Data Structures and Algorithms Social and Information Networks
Sketch-based Influence Maximization and Computation: Scaling up with Guarantees
The gold standard for Influence Maximization is the greedy algorithm, which iteratively adds to the seed set a node maximizing the marginal gain in influence.
Data Structures and Algorithms Social and Information Networks G.2.2; H.2.8
Sample Complexity Bounds for Influence Maximization
Our main result is a surprising upper bound of $O( s \tau \epsilon^{-2} \ln \frac{n}{\delta})$ for a broad class of models that includes IC and LT models and their mixtures, where $n$ is the number of nodes and $\tau$ is the number of diffusion steps.
Graph Learning with Loss-Guided Training
Classically, ML models trained with stochastic gradient descent (SGD) are designed to minimize the average loss per example and use a distribution of training examples that remains {\em static} in the course of training.
WOR and $p$'s: Sketches for $\ell_p$-Sampling Without Replacement
We design novel composable sketches for WOR $\ell_p$ sampling, weighted sampling of keys according to a power $p\in[0, 2]$ of their frequency (or for signed data, sum of updates).
Differentially Private Weighted Sampling
A weighted sample of keys by (a function of) frequency is a highly versatile summary that provides a sparse set of representative keys and supports approximate evaluations of query statistics.
A Framework for Adversarial Streaming via Differential Privacy and Difference Estimators
Classical streaming algorithms operate under the (not always reasonable) assumption that the input stream is fixed in advance.
FriendlyCore: Practical Differentially Private Aggregation
Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results.
Differentially-Private Clustering of Easy Instances
Clustering is a fundamental problem in data analysis.
On the Robustness of CountSketch to Adaptive Inputs
CountSketch is a popular dimensionality reduction technique that maps vectors to a lower dimension using randomized linear measurements.
Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive Inputs
When inputs are adaptive, however, an adversarial input can be constructed after $O(\ell)$ queries with the classic estimator and the best known robust estimator only supports $\tilde{O}(\ell^2)$ queries.
Õptimal Differentially Private Learning of Thresholds and Quasi-Concave Optimization
The problem of learning threshold functions is a fundamental one in machine learning.
Hot PATE: Private Aggregation of Distributions for Diverse Task
Until now, PATE has primarily been explored with classification-like tasks, where each example possesses a ground-truth label, and knowledge is transferred to the student by labeling public examples.
Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold Queries
One of the most basic problems for studying the "price of privacy over time" is the so called private counter problem, introduced by Dwork et al. (2010) and Chan et al. (2010).
