Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues

In this work we derive a variant of the classic Glivenko-Cantelli Theorem, which asserts uniform convergence of the empirical Cumulative Distribution Function (CDF) to the CDF of the underlying distribution. Our variant allows for tighter convergence bounds for extreme values of the CDF. We apply our bound in the context of revenue learning, which is a well-studied problem in economics and algorithmic game theory. We derive sample-complexity bounds on the uniform convergence rate of the empirical revenues to the true revenues, assuming a bound on the $k$th moment of the valuations, for any (possibly fractional) $k>1$. For uniform convergence in the limit, we give a complete characterization and a zero-one law: if the first moment of the valuations is finite, then uniform convergence almost surely occurs; conversely, if the first moment is infinite, then uniform convergence almost never occurs.

[1]  M. Borel Les probabilités dénombrables et leurs applications arithmétiques , 1909 .

[2]  J. Kiefer,et al.  Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator , 1956 .

[3]  Z. Birnbaum,et al.  A Distribution-Free Upper Confidence Bound for $\Pr \{Y < X\}$, Based on Independent Samples of $X$ and $Y$ , 1958 .

[4]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[5]  Roger B. Myerson,et al.  Optimal Auction Design , 1981, Math. Oper. Res..

[6]  P. Massart The Tight Constant in the Dvoretzky-Kiefer-Wolfowitz Inequality , 1990 .

[7]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[8]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[9]  V. Koltchinskii,et al.  Rademacher Processes and Bounding the Risk of Function Learning , 2004, math/0405338.

[10]  Peter L. Bartlett,et al.  Rademacher and Gaussian Complexities: Risk Bounds and Structural Results , 2003, J. Mach. Learn. Res..

[11]  Yishay Mansour,et al.  Learning Bounds for Importance Weighting , 2010, NIPS.

[12]  Tim Roughgarden,et al.  Revenue maximization with a single sample , 2010, EC '10.

[13]  Richard Cole,et al.  The sample complexity of revenue maximization , 2014, STOC.

[14]  Tim Roughgarden,et al.  On the Pseudo-Dimension of Nearly Optimal Auctions , 2015, NIPS.

[15]  Tim Roughgarden,et al.  Making the Most of Your Samples , 2014, EC.

[16]  Tim Roughgarden,et al.  The Pseudo-Dimension of Near-Optimal Auctions , 2015, NIPS 2015.

[17]  Tim Roughgarden,et al.  Learning Simple Auctions , 2016, COLT.

[18]  Maria-Florina Balcan,et al.  Sample Complexity of Automated Mechanism Design , 2016, NIPS.

[19]  Tim Roughgarden,et al.  Ironing in the Dark , 2015, EC.

[20]  Nikhil R. Devanur,et al.  The sample complexity of auctions with side information , 2015, STOC.

[21]  Yannai A. Gonczarowski,et al.  Efficient empirical revenue maximization in single-parameter auction environments , 2016, STOC.

[22]  Mehryar Mohri,et al.  Relative deviation learning bounds and generalization with unbounded loss functions , 2013, Annals of Mathematics and Artificial Intelligence.