Online Algorithms with Limited Data Retention

• URL: http://arxiv.org/abs/2404.10997v1
• Date: Wed, 17 Apr 2024 02:17:23 GMT
• Title: Online Algorithms with Limited Data Retention
• Authors: Nicole Immorlica, Brendan Lucier, Markus Mobius, James Siderius,
• Abstract summary: We introduce a model of online algorithms subject to strict constraints on data retention. We show it is possible to obtain an exponential improvement over a baseline algorithm that retains all data as long as possible. One implication of our results is that data retention laws are insufficient to guarantee the right to be forgotten.
• Score: 4.101276693704335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a model of online algorithms subject to strict constraints on data retention. An online learning algorithm encounters a stream of data points, one per round, generated by some stationary process. Crucially, each data point can request that it be removed from memory $m$ rounds after it arrives. To model the impact of removal, we do not allow the algorithm to store any information or calculations between rounds other than a subset of the data points (subject to the retention constraints). At the conclusion of the stream, the algorithm answers a statistical query about the full dataset. We ask: what level of performance can be guaranteed as a function of $m$? We illustrate this framework for multidimensional mean estimation and linear regression problems. We show it is possible to obtain an exponential improvement over a baseline algorithm that retains all data as long as possible. Specifically, we show that $m = \textsc{Poly}(d, \log(1/\epsilon))$ retention suffices to achieve mean squared error $\epsilon$ after observing $O(1/\epsilon)$ $d$-dimensional data points. This matches the error bound of the optimal, yet infeasible, algorithm that retains all data forever. We also show a nearly matching lower bound on the retention required to guarantee error $\epsilon$. One implication of our results is that data retention laws are insufficient to guarantee the right to be forgotten even in a non-adversarial world in which firms merely strive to (approximately) optimize the performance of their algorithms. Our approach makes use of recent developments in the multidimensional random subset sum problem to simulate the progression of stochastic gradient descent under a model of adversarial noise, which may be of independent interest.

Related papers

• On the Convergence of a Federated Expectation-Maximization Algorithm [0.0]
  We study the convergence rate of the Expectation-Maximization (EM) algorithm for the Federated Mixture of $K$ Linear Regressions model. Surprisingly, the results show that rather than being a bottleneck, data heterogeneity can accelerate the convergence of Federated Learning algorithms.
  arXiv  Detail & Related papers  (2024-08-11T16:46:42Z)
• Private Geometric Median [10.359525525715421]
  We study differentially private (DP) algorithms for computing the geometric median (GM) of a dataset. Our main contribution is a pair of DP algorithms for the task of private GM with an excess error guarantee that scales with the effective diameter of the datapoints.
  arXiv  Detail & Related papers  (2024-06-11T16:13:09Z)
• Turnstile $\ell_p$ leverage score sampling with applications [56.403488578703865]
  We develop a novel algorithm for sampling rows $a_i$ of a matrix $AinmathbbRntimes d$, proportional to their $ell_p$ norm, when $A$ is presented in a turnstile data stream. Our algorithm not only returns the set of sampled row indexes, it also returns slightly perturbed rows $tildea_i approx a_i$, and approximates their sampling probabilities up to $varepsilon$ relative error. For logistic regression, our framework yields the first algorithm that achieves a $
  arXiv  Detail & Related papers  (2024-06-01T07:33:41Z)
• Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic [99.3682210827572]
  Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets. Data curation strategies are typically developed agnostic of the available compute for training. We introduce neural scaling laws that account for the non-homogeneous nature of web data.
  arXiv  Detail & Related papers  (2024-04-10T17:27:54Z)
• Deterministic Nonsmooth Nonconvex Optimization [94.01526844386977]
  We show that randomization is necessary to obtain a dimension-free dimension-free algorithm. Our algorithm yields the first deterministic dimension-free algorithm for optimizing ReLU networks.
  arXiv  Detail & Related papers  (2023-02-16T13:57:19Z)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Scalable Differentially Private Clustering via Hierarchically Separated Trees [82.69664595378869]
  We show that our method computes a solution with cost at most $O(d3/2log n)cdot OPT + O(k d2 log2 n / epsilon2)$, where $epsilon$ is the privacy guarantee. Although the worst-case guarantee is worse than that of state of the art private clustering methods, the algorithm we propose is practical.
  arXiv  Detail & Related papers  (2022-06-17T09:24:41Z)
• Differentially Private Federated Learning via Inexact ADMM [0.0]
  Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks. We develop a DP inexact alternating direction method of multipliers algorithm that solves a sequence of trust-region subproblems. Our algorithm reduces the testing error by at most $22%$ compared with the existing DP algorithm, while achieving the same level of data privacy.
  arXiv  Detail & Related papers  (2021-06-11T02:28:07Z)
• An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling [83.48992319018147]
  We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. A natural way to resolve this problem is to apply online gradient descent (SGD) so that the per-step time and memory complexity can be reduced to constant. In this work, we show that online SGD can be applied to the generalized linear bandit problem. The proposed SGD-TS algorithm, which uses a single-step SGD update to exploit past information, achieves $tildeO(sqrtT)$ regret with the total time complexity that
  arXiv  Detail & Related papers  (2020-06-07T01:12:39Z)
• A Deterministic Streaming Sketch for Ridge Regression [15.256452294422294]
  We provide a deterministic space-efficient algorithm for estimating ridge regression. This is the first $o(d2)$ space deterministic streaming algorithm with guaranteed solution error. In comparisons to randomized sketching algorithms on synthetic and real-world datasets, our algorithm has less empirical error using less space and similar time.
  arXiv  Detail & Related papers  (2020-02-05T22:08:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.