arXiv subjects

Ananda Theertha Suresh

Publications and source records attributed to Ananda Theertha Suresh.

At least 73 records · Page 4Linked to original sources

arXiv2019

Can You Really Backdoor Federated Learning?

The decentralized nature of federated learning makes detecting and defending against adversarial attacks a challenging task. This paper focuses on backdoor attacks in the federated learning setting, where the goal of the adversary is to reduce the performance of the model on targeted tasks while maintaining good performance on the main task. Unlike existing works, we allow non-malicious clients to have correctly labeled samples from the targeted tasks. We conduct a comprehensive study of backdoor attacks and defenses for the EMNIST dataset, a real-life, user-partitioned, and non-iid dataset. We observe that in the absence of defenses, the performance of the attack largely depends on the fraction of adversaries present and the "complexity'' of the targeted task. Moreover, we show that norm clipping and "weak'' differential privacy mitigate the attacks without hurting the overall performance. We have implemented the attacks and defenses in TensorFlow Federated (TFF), a TensorFlow framework for federated learning. In open-sourcing our code, our goal is to encourage researchers to contribute new attacks and defenses and evaluate them on standard federated datasets.

cs.LG↗

arXiv2019

AdaCliP: Adaptive Clipping for Private SGD

Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models have been proposed. At each step, these algorithms modify the gradients and add noise proportional to the sensitivity of the modified gradients. Under this framework, we propose AdaCliP, a theoretically motivated differentially private SGD algorithm that provably adds less noise compared to the previous methods, by using coordinate-wise adaptive clipping of the gradient. We empirically demonstrate that AdaCliP reduces the amount of added noise and produces models with better accuracy.

cs.LG↗

arXiv2019

Optimal multiclass overfitting by sequence reconstruction from Hamming queries

A primary concern of excessive reuse of test datasets in machine learning is that it can lead to overfitting. Multiclass classification was recently shown to be more resistant to overfitting than binary classification. In an open problem of COLT 2019, Feldman, Frostig, and Hardt ask to characterize the dependence of the amount of overfitting bias with the number of classes $m$, the number of accuracy queries $k$, and the number of examples in the dataset $n$. We resolve this problem and determine the amount of overfitting possible in multi-class classification. We provide computationally efficient algorithms that achieve overfitting bias of $\tildeΘ(\max\{\sqrt{{k}/{(mn)}}, k/n\})$, matching the known upper bounds.

cs.LG↗

arXiv2019

Federated Learning of N-gram Language Models

We propose algorithms to train production-quality n-gram language models using federated learning. Federated learning is a distributed computation platform that can be used to train global models for portable devices such as smart phones. Federated learning is especially relevant for applications handling privacy-sensitive data, such as virtual keyboards, because training is performed without the users' data ever leaving their devices. While the principles of federated learning are fairly generic, its methodology assumes that the underlying models are neural networks. However, virtual keyboards are typically powered by n-gram language models for latency reasons. We propose to train a recurrent neural network language model using the decentralized FederatedAveraging algorithm and to approximate this federated model server-side with an n-gram model that can be deployed to devices for fast inference. Our technical contributions include ways of handling large vocabularies, algorithms to correct capitalization errors in user data, and efficient finite state transducer algorithms to convert word language models to word-piece language models and vice versa. The n-gram language models trained with federated learning are compared to n-grams trained with traditional server-based algorithms using A/B tests on tens of millions of users of virtual keyboard. Results are presented for two languages, American English and Brazilian Portuguese. This work demonstrates that high-quality n-gram language models can be trained directly on client mobile devices without sensitive training data ever leaving the devices.

cs.CL↗

arXiv2019

Agnostic Federated Learning

A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions. We further show that this framework naturally yields a notion of fairness. We present data-dependent Rademacher complexity guarantees for learning with this objective, which guide the definition of an algorithm for agnostic federated learning. We also give a fast stochastic optimization algorithm for solving the corresponding optimization problem, for which we prove convergence bounds, assuming a convex loss function and hypothesis set. We further empirically demonstrate the benefits of our approach in several datasets. Beyond federated learning, our framework and algorithm can be of interest to other learning scenarios such as cloud computing, domain adaptation, drifting, and other contexts where the training and test distributions do not coincide.

cs.LG↗

arXiv2018

WEST: Word Encoded Sequence Transducers

Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic speech recognition (ASR). One way of compressing the embedding and softmax layers is to substitute larger units such as words with smaller sub-units such as characters. However, often the sub-unit models perform poorly compared to the larger unit models. We propose WEST, an algorithm for encoding categorical features and output classes with a sequence of random or domain dependent sub-units and demonstrate that this transduction can lead to significant compression without compromising performance. WEST bridges the gap between larger unit and sub-unit models and can be interpreted as a MaxEnt model over sub-unit features, which can be of independent interest.

cs.LG↗

arXiv2018

cpSGD: Communication-efficient and differentially-private distributed SGD

Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy of the clients. Several recent works have focused on reducing the communication cost or introducing privacy guarantees, but none of the proposed communication efficient methods are known to be privacy preserving and none of the known privacy mechanisms are known to be communication efficient. To this end, we study algorithms that achieve both communication efficiency and differential privacy. For $d$ variables and $n \approx d$ clients, the proposed method uses $O(\log \log(nd))$ bits of communication per client per coordinate and ensures constant privacy. We also extend and improve previous analysis of the \emph{Binomial mechanism} showing that it achieves nearly the same utility as the Gaussian mechanism, while requiring fewer representation bits, which can be of independent interest.

stat.ML↗

arXiv2017

Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition

Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with new variants on a YouTube speech recognition task. Lattice rescoring using LSTMLMs reduces the word error rate (WER) for this task by 8\% relative to the WER obtained using an N-gram LM.

stat.ML↗

arXiv2017

Federated Learning: Strategies for Improving Communication Efficiency

Federated Learning is a machine learning setting where the goal is to train a high-quality centralized model while training data remains distributed over a large number of clients each with unreliable and relatively slow network connections. We consider learning algorithms for this setting where on each round, each client independently computes an update to the current model based on its local data, and communicates this update to a central server, where the client-side updates are aggregated to compute a new global model. The typical clients in this setting are mobile phones, and communication efficiency is of the utmost importance. In this paper, we propose two ways to reduce the uplink communication costs: structured updates, where we directly learn an update from a restricted space parametrized using a smaller number of variables, e.g. either low-rank or a random mask; and sketched updates, where we learn a full model update and then compress it using a combination of quantization, random rotations, and subsampling before sending it to the server. Experiments on both convolutional and recurrent networks show that the proposed methods can reduce the communication cost by two orders of magnitude.

cs.LG↗

arXiv2017

Distributed Mean Estimation with Limited Communication

Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data with $n$ clients, a naive stochastic binary rounding approach yields a mean squared error (MSE) of $Θ(d/n)$ and uses a constant number of bits per dimension per client. We then extend this naive algorithm in two ways: we show that applying a structured random rotation before quantization reduces the error to $\mathcal{O}((\log d)/n)$ and a better coding strategy further reduces the error to $\mathcal{O}(1/n)$ and uses a constant number of bits per dimension per client. We also show that the latter coding strategy is optimal up to a constant in the minimax sense i.e., it achieves the best MSE for a given communication cost. We finally demonstrate the practicality of our algorithms by applying them to distributed Lloyd's algorithm for k-means and power iteration for PCA.

cs.LG↗

arXiv2017

Model-Powered Conditional Independence Test

We consider the problem of non-parametric Conditional Independence testing (CI testing) for continuous random variables. Given i.i.d samples from the joint distribution $f(x,y,z)$ of continuous random vectors $X,Y$ and $Z,$ we determine whether $X \perp Y | Z$. We approach this by converting the conditional independence test into a classification problem. This allows us to harness very powerful classifiers like gradient-boosted trees and deep neural networks. These models can handle complex probability distributions and allow us to perform significantly better compared to the prior state of the art, for high-dimensional CI testing. The main technical challenge in the classification problem is the need for samples from the conditional product distribution $f^{CI}(x,y,z) = f(x|z)f(y|z)f(z)$ -- the joint distribution if and only if $X \perp Y | Z.$ -- when given access only to i.i.d. samples from the true joint distribution $f(x,y,z)$. To tackle this problem we propose a novel nearest neighbor bootstrap procedure and theoretically show that our generated samples are indeed close to $f^{CI}$ in terms of total variational distance. We then develop theoretical results regarding the generalization bounds for classification for our problem, which translate into error bounds for CI testing. We provide a novel analysis of Rademacher type classification bounds in the presence of non-i.i.d near-independent samples. We empirically validate the performance of our algorithm on simulated and real datasets and show performance gains over previous methods.

stat.ML↗

arXiv2017

Maximum Selection and Ranking under Noisy Comparisons

We consider $(ε,δ)$-PAC maximum-selection and ranking for general probabilistic models whose comparisons probabilities satisfy strong stochastic transitivity and stochastic triangle inequality. Modifying the popular knockout tournament, we propose a maximum-selection algorithm that uses $\mathcal{O}\left(\frac{n}{ε^2}\log \frac{1}δ\right)$ comparisons, a number tight up to a constant factor. We then derive a general framework that improves the performance of many ranking algorithms, and combine it with merge sort and binary search to obtain a ranking algorithm that uses $\mathcal{O}\left(\frac{n\log n (\log \log n)^3}{ε^2}\right)$ comparisons for any $δ\ge\frac1n$, a number optimal up to a $(\log \log n)^3$ factor.

cs.LG↗

arXiv2017

Minimax Risk for Missing Mass Estimation

The problem of estimating the missing mass or total probability of unseen elements in a sequence of $n$ random samples is considered under the squared error loss function. The worst-case risk of the popular Good-Turing estimator is shown to be between $0.6080/n$ and $0.6179/n$. The minimax risk is shown to be lower bounded by $0.25/n$. This appears to be the first such published result on minimax risk for estimation of missing mass, which has several practical and theoretical applications.

cs.IT↗

arXiv2016

A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation

The advent of data science has spurred interest in estimating properties of distributions over large alphabets. Fundamental symmetric properties such as support size, support coverage, entropy, and proximity to uniformity, received most attention, with each property estimated using a different technique and often intricate analysis tools. We prove that for all these properties, a single, simple, plug-in estimator---profile maximum likelihood (PML)---performs as well as the best specialized techniques. This raises the possibility that PML may optimally estimate many other symmetric properties.

cs.IT↗

arXiv2016

Orthogonal Random Features

We present an intriguing discovery related to Random Fourier Features: in Gaussian kernel approximation, replacing the random Gaussian matrix by a properly scaled random orthogonal matrix significantly decreases kernel approximation error. We call this technique Orthogonal Random Features (ORF), and provide theoretical and empirical justification for this behavior. Motivated by this discovery, we further propose Structured Orthogonal Random Features (SORF), which uses a class of structured discrete orthogonal matrices to speed up the computation. The method reduces the time cost from $\mathcal{O}(d^2)$ to $\mathcal{O}(d \log d)$, where $d$ is the data dimensionality, with almost no compromise in kernel approximation quality compared to ORF. Experiments on several datasets verify the effectiveness of ORF and SORF over the existing methods. We also provide discussions on using the same type of discrete orthogonal structure for a broader range of applications.

cs.LG↗

arXiv2016

Maximum Selection and Sorting with Adversarial Comparators and an Application to Density Estimation

We study maximum selection and sorting of $n$ numbers using pairwise comparators that output the larger of their two inputs if the inputs are more than a given threshold apart, and output an adversarially-chosen input otherwise. We consider two adversarial models. A non-adaptive adversary that decides on the outcomes in advance based solely on the inputs, and an adaptive adversary that can decide on the outcome of each query depending on previous queries and outcomes. Against the non-adaptive adversary, we derive a maximum-selection algorithm that uses at most $2n$ comparisons in expectation, and a sorting algorithm that uses at most $2n \ln n$ comparisons in expectation. These numbers are within small constant factors from the best possible. Against the adaptive adversary, we propose a maximum-selection algorithm that uses $Θ(n\log (1/ε))$ comparisons to output a correct answer with probability at least $1-ε$. The existence of this algorithm affirmatively resolves an open problem of Ajtai, Feldman, Hassadim, and Nelson. Our study was motivated by a density-estimation problem where, given samples from an unknown underlying distribution, we would like to find a distribution in a known class of $n$ candidate distributions that is close to underlying distribution in $\ell_1$ distance. Scheffe's algorithm outputs a distribution at an $\ell_1$ distance at most 9 times the minimum and runs in time $Θ(n^2\log n)$. Using maximum selection, we propose an algorithm with the same approximation guarantee but run time of $Θ(n\log n)$.

cs.DS↗

arXiv2016

Estimating Renyi Entropy of Discrete Distributions

It was recently shown that estimating the Shannon entropy $H({\rm p})$ of a discrete $k$-symbol distribution ${\rm p}$ requires $Θ(k/\log k)$ samples, a number that grows near-linearly in the support size. In many applications $H({\rm p})$ can be replaced by the more general Rényi entropy of order $α$, $H_α({\rm p})$. We determine the number of samples needed to estimate $H_α({\rm p})$ for all $α$, showing that $α< 1$ requires a super-linear, roughly $k^{1/α}$ samples, noninteger $α>1$ requires a near-linear $k$ samples, but, perhaps surprisingly, integer $α>1$ requires only $Θ(k^{1-1/α})$ samples. Furthermore, developing on a recently established connection between polynomial approximation and estimation of additive functions of the form $\sum_{x} f({\rm p}_x)$, we reduce the sample complexity for noninteger values of $α$ by a factor of $\log k$ compared to the empirical estimator. The estimators achieving these bounds are simple and run in time linear in the number of samples. Our lower bounds provide explicit constructions of distributions with different Rényi entropies that are hard to distinguish.

cs.IT↗

arXiv2016

Estimating the number of unseen species: A bird in the hand is worth $\log n $ in the bush

Estimating the number of unseen species is an important problem in many scientific endeavors. Its most popular formulation, introduced by Fisher, uses $n$ samples to predict the number $U$ of hitherto unseen species that would be observed if $t\cdot n$ new samples were collected. Of considerable interest is the largest ratio $t$ between the number of new and existing samples for which $U$ can be accurately predicted. In seminal works, Good and Toulmin constructed an intriguing estimator that predicts $U$ for all $t\le 1$, thereby showing that the number of species can be estimated for a population twice as large as that observed. Subsequently Efron and Thisted obtained a modified estimator that empirically predicts $U$ even for some $t>1$, but without provable guarantees. We derive a class of estimators that $\textit{provably}$ predict $U$ not just for constant $t>1$, but all the way up to $t$ proportional to $\log n$. This shows that the number of species can be estimated for a population $\log n$ times larger than that observed, a factor that grows arbitrarily large as $n$ increases. We also show that this range is the best possible and that the estimators' mean-square error is optimal up to constants for any $t$. Our approach yields the first provable guarantee for the Efron-Thisted estimator and, in addition, a variant which achieves stronger theoretical and experimental performance than existing methodologies on a variety of synthetic and real datasets. The estimators we derive are simple linear estimators that are computable in time proportional to $n$. The performance guarantees hold uniformly for all distributions, and apply to all four standard sampling models commonly used across various scientific disciplines: multinomial, Poisson, hypergeometric, and Bernoulli product.

math.ST↗