Uniform Convergence Bounds for Codec Selection

We frame the problem of selecting an optimal audio encoding scheme as a supervised learning task. Through uniform convergence theory, we guarantee approximately optimal codec selection while controlling for selection bias. We present rigorous statistical guarantees for the codec selection problem that hold for arbitrary distributions over audio sequences and for arbitrary quality metrics. Our techniques can thus balance sound quality and compression ratio, and use audio samples from the distribution to select a codec that performs well on that particular type of data. The applications of our technique are immense, as it can be used to optimize for quality and bandwidth usage of streaming and other digital media, while significantly outperforming approaches that apply a fixed codec to all data sources.

[1]  Eli Upfal,et al.  ABRA: Approximating Betweenness Centrality in Static and Dynamic Graphs with Rademacher Averages , 2016, KDD.

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

[3]  Tapio Elomaa,et al.  Progressive rademacher sampling , 2002, AAAI/IAAI.

[4]  Kevin Leyton-Brown,et al.  Sequential Model-Based Optimization for General Algorithm Configuration , 2011, LION.

[5]  B. Efron,et al.  The Jackknife Estimate of Variance , 1981 .

[6]  Eli Upfal,et al.  Mining Frequent Itemsets through Progressive Sampling with Rademacher Averages , 2015, KDD.

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

[8]  Martin Holters,et al.  GSTPEAQ – AN OPEN SOURCE IMPLEMENTATION OF THE PEAQ ALGORITHM , 2015 .

[9]  Tim Kraska,et al.  The Case for Learned Index Structures , 2018 .

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

[11]  T. Philips,et al.  The Moment Bound is Tighter than Chernoff's Bound for Positive Tail Probabilities , 1995 .

[12]  Tim Roughgarden,et al.  A PAC Approach to Application-Specific Algorithm Selection , 2015, SIAM J. Comput..

[13]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

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

[15]  Thomas Sporer,et al.  PEAQ - The ITU Standard for Objective Measurement of Perceived Audio Quality , 2000 .

[16]  Vladimir Koltchinskii,et al.  Rademacher penalties and structural risk minimization , 2001, IEEE Trans. Inf. Theory.

[17]  Peter L. Bartlett,et al.  Model Selection and Error Estimation , 2000, Machine Learning.

[18]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[19]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[20]  Colin McDiarmid,et al.  Surveys in Combinatorics, 1989: On the method of bounded differences , 1989 .

[21]  Robert J. Safranek,et al.  Signal compression based on models of human perception , 1993, Proc. IEEE.

[22]  B. M. Brown,et al.  Martingale Central Limit Theorems , 1971 .

[23]  P. Bartlett,et al.  Local Rademacher complexities , 2005, math/0508275.

[24]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[25]  G. Bennett.  Probability Inequalities for the Sum of Independent Random Variables , 1962 .