Convergence of stochastic processes
By D. Pollard. 1984
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Victor Chernozhukov
- Sergey Levine
- Francis R. Bach
- Michael I. Jordan
- Dacheng Tao
- Ruslan Salakhutdinov
- Trevor Darrell
Citations in the corpus
- DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections (2019, neutral): “[35] D Pollard.”
- Nonparametric Tests for Common Values at First-Price Sealed-Bid Auctions (2004, unknown): “1 Bid Preparation Costs Samuelson (1985) studied a model in which bidders rst observe their signals and the reserve price , then decide whether to incur a cost of preparing a bid.”
- Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards (2010, methodology): “e expected regret under the LLR policy is at most " 4a2 maxL 2(L+1)N lnn (∆min) 2 +N + π2 3 LN # ∆max. (7) 5 To proof Theorem 2, we use the inequalities as stated in the Chernoff-Hoeffding bound [17]. Lemma 1 (Chernoff-Hoeffding bound [17]): X1,...,Xn are random variables with range [0,1], and ”
- Asymptotic Normality of Semiparametric and Nonparametric Posterior Distributions (2002, background): “The second compares the log-likelihood at different parameter values to characterize the behavior of a maximizer (cf. Pollard 1984, chap.”
- On Profile Likelihood (2000, background): “Parametric versions of some of these corollaries have appeared many times (see, e.g., Chernoff 1954; Pollard 1984, chap.”
- Trimmed means for functional data (2001, unknown): “NI(E, Pn, 5) is the family's entropy. (see Pollard 1984, Theorem 24 pp. 25).”
- Testing relevant hypotheses in functional time series via self‐normalization (2018, methodology): “By an application of Example 11 in Chapter IV of Pollard (1984) it suffices to prove that (i) Σm → Σ as m→∞.”
- On the Concept of Depth for Functional Data (2009, background): “‘ (see Pollard, 1984)].”
- Toward Efficient Agnostic Learning (1992, background): “When is empirical minimization sufficient for agnostic learning? This question has been answered in large part by Dudley [4], Haussler [6], Pollard [ 14 ], Vapnik [18] and others.”