25th Annual Conference on Learning Theory Differentially Private Online Learning

Citations in the corpus

• Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity (2018, methodology): “That work proposed a privacy-preserving mechanisms in the central model of differential privacy, later extended and applied by Chan et al. [CSS11] and Jain et al. [JKT12].”
• Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds (2014, background): “Variants of Algorithm ANoise−GD have appeared in [49, 28, 17, 47].”
• Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries (2015, background): “first making explicit the connection between probabilistic inference and differential privacy [24, 13].”
• Towards Practical Differentially Private Convex Optimization (2019, neutral): “Many recent works [30], [31], [32] examine the setting of online learning, whereas highdimensional kernel learning is considered in [33]; these settings are quite different from ours, and the results are incomparable.”
• The Price of Differential Privacy for Online Learning (2017, methodology): “The Price of Differential Privacy for Online Learning Algorithm 2 TreeBasedAgg(lt, B, t,D, T ) input Loss vector lt, Binary tree B, Round t, Noise distribution D, Time horizon T 1: (L̃′t, B) ← PrivateSum(lt, B, t,D, T ) – Algorithm 5 ((Jain et al., 2012)) with the noise added at each node – be it in”
• Private Empirical Risk Minimization, Revisited (2014, background): “Variants of Algorithm ANoise−GD have appeared in [41, 24, 11, 40].”
• The Large Margin Mechanism for Differentially Private Maximization (2014, background): “There has been a large amount of work on differential privacy for a wide range of statistical and machine learning tasks over the last decade [6, 30, 13, 21, 33, 24, 1]; for overviews, see [18] and [29].”
• Online Learning via the Differential Privacy Lens (2017, unknown): “We emphasize that our aim is not to design low-regret algorithms that satisfy the privacy condition– there is already substantial existing work along these lines [4, 21, 39, 40].”
• Optimal Noise Adding Mechanisms for Approximate Differential Privacy (2013, methodology): “using ∞ metric in [7] and [26], while in our work we use 1 metric.”
• Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning (2017, background): “, data collection [19], spatiotemporal correlations [20, 21], data streams [22], stochastic gradient descents [23], recommendation [7], regression [6], online learning [24], publishing contingency tables [25], and spectral graph analysis [26].”
• Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization (2018, background): “Many works have shown that differential privacy can be used to enable privacy-preserving machine learning in the centralized setting where a single organization owns all the data [10, 11, 29, 30, 51, 58].”
• The Interplay Between Stability and Regret in Online Learning (2012, background): “For instance, stability allows us to derive guarantees that apply to dependent (non-iid) data [2] and is critical in areas such as privacy [11].”
• Differentially Private Empirical Risk Minimization Revisited: Faster and More General (2018, background): “[17][30] and [2] investigated regret bound in online settings.”
• Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses (2020, background): “…private convex optimization has been studied extensively for over a decade (see, e.g., (Chaudhuri and Monteleoni, 2008; Chaudhuri et al., 2011; Jain et al., 2012; Kifer et al., 2012; Smith and Thakurta, 2013; Bassily et al., 2014; Ullman, 2015; Jain and Thakurta, 2014; Talwar et al., 2015;…”