Private and Online Learnability Are Equivalent
نویسندگان
چکیده
Let H be a binary-labeled concept class. We prove that can PAC learned by an (approximate) differentially private algorithm if and only it has finite Littlestone dimension. This implies qualitative equivalence between online learnability learnability.
منابع مشابه
Agnostic Online learnability
We study a fundamental question. What classes of hypotheses are learnable in the online learning model? The analogous question in the PAC learning model [12] was addressed by Vapnik and others [13], who showed that the VC dimension characterizes the learnability of a hypothesis class. In his influential work, Littlestone [9] studied the online learnability of hypothesis classes, but only in the...
متن کاملOnline Inertia Constant and Thévenin Equivalent Estimation Using PMU Data
In this paper a new algorithm based on phasor measurements for estimating the Thévenin Equivalent (TE) and system inertia constant is proposed. The method estimates the network TE seen from a generator terminal and equivalent system inertia constant by means of phasor data that is available at Phasor Data Concentrator (PDC) center. It is shown that the parameters of the TE could be estimated at...
متن کاملStability Conditions for Online Learnability
Stability is a general notion that quantifies the sensitivity of a learning algorithm’s output to small change in the training dataset (e.g. deletion or replacement of a single training sample). Such conditions have recently been shown to be more powerful to characterize learnability in the general learning setting under i.i.d. samples where uniform convergence is not necessary for learnability...
متن کاملonline inertia constant and thévenin equivalent estimation using pmu data
in this paper a new algorithm based on phasor measurements for estimating the thévenin equivalent (te) and system inertia constant is proposed. the method estimates the network te seen from a generator terminal and equivalent system inertia constant by means of phasor data that is available at phasor data concentrator (pdc) center. it is shown that the parameters of the te could be estimated at...
متن کاملOnline Learning: Random Averages, Combinatorial Parameters, and Learnability
We study learnability in the online learning model. We define several complexity measures which capture the difficulty of learning in a sequential manner. Among these measures are analogues of Rademacher complexity, covering numbers and fat shattering dimension from statistical learning theory. Relationship among these complexity measures, their connection to online learning, and tools for boun...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of the ACM
سال: 2022
ISSN: ['0004-5411', '1557-735X']
DOI: https://doi.org/10.1145/3526074