• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

Universal coding on infinite alphabets: exponentially decreasing envelopes (2011)

by D Bontemps
Venue:IEEE Trans. Inform. Theory
Add To MetaCart

Tools

Sorted by:
Results 1 - 8 of 8

About Adaptive Coding on Countable Alphabets

by Dominique Bontemps, Stéphane Boucheron, Elisabeth Gassiat , 2012
"... This paper sheds light on universal coding with respect to classes of memoryless sources over a countable alphabet defined by an envelope function with finite and non-decreasing hazard rate. We prove that the auto-censuring (AC) code introduced by Bontemps (2011) is adaptive with respect to the coll ..."
Abstract - Cited by 5 (1 self) - Add to MetaCart
This paper sheds light on universal coding with respect to classes of memoryless sources over a countable alphabet defined by an envelope function with finite and non-decreasing hazard rate. We prove that the auto-censuring (AC) code introduced by Bontemps (2011) is adaptive with respect to the collection of such classes. The analysis builds on the tight characterization of universal redundancy rate in terms of metric entropy by Haussler and Opper (1997) and on a careful analysis of the performance of the AC-coding algorithm. The latter relies on non-asymptotic bounds for maxima of samples from discrete distributions with finite and non-decreasing hazard rate.
(Show Context)

Citation Context

...es. We provide positive and precise answers to the aforementioned questions for a family of envelope classes that lie between the exponential envelope classes investigated in (Boucheron et al., 2009; =-=Bontemps, 2011-=-) and the classes of sources with finite alphabets. Haussler and Opper (1997) characterize the minimax redundancy of a collection of sources using the metric entropy of the class of marginal distribut...

Poissonization and universal compression of envelope classes

by Jayadev Acharya, Ashkan Jafarpour, Alon Orlitsky, A Theertha Suresh
"... Abstract—Poisson sampling is a method for eliminating de-pendence among symbols in a random sequence. It helps im-prove algorithm design, strengthen bounds, and simplify proofs. We relate the redundancy of fixed-length and Poisson-sampled sequences, use this result to derive a simple formula for the ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
Abstract—Poisson sampling is a method for eliminating de-pendence among symbols in a random sequence. It helps im-prove algorithm design, strengthen bounds, and simplify proofs. We relate the redundancy of fixed-length and Poisson-sampled sequences, use this result to derive a simple formula for the redundancy of general envelope classes, and apply this formula to obtain simple and tight bounds on the redundancy of power-law and exponential envelope classes, in particular answering a question posed in [1]. I.
(Show Context)

Citation Context

... ≤ R̂(Λnc·−α) ≤ ( 2cn α− 1 ) 1 α (log n)1− 1 α +O(1), (1) where C0 is a constant (function of α and c). For exponential envelopes they prove that log2 n 8α (1 + o(1)) ≤ R̂(Λnce−α·) ≤ log2 n 2α +O(1). =-=[24]-=- improve the bounds for Λnce−α· and show that R̂(Λnce−α·) = log2 n 4α +O(log n log log n). More recently, [25] extend the arguments of [24] to find tight universal codes for the larger class of sub-ex...

1Large Alphabet Compression and Predictive Distributions through Poissonization and Tilting

by Xiao Yang, Student Member, Ieee Andrew, R. Barron
"... This paper introduces a convenient strategy for coding and predicting sequences of independent, identically distributed random variables generated from a large alphabet of size m. In particular, the size of the sample is allowed to be variable. The employment of a Poisson model and tilting method si ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
This paper introduces a convenient strategy for coding and predicting sequences of independent, identically distributed random variables generated from a large alphabet of size m. In particular, the size of the sample is allowed to be variable. The employment of a Poisson model and tilting method simplifies the implementation and analysis through independence. The resulting strategy is optimal within the class of distributions satisfying a moment condition, and is close to optimal for the class of all i.i.d distributions on strings of a given length. Moreover, the method can be used to code and predict strings with a condition on the tail of the ordered counts. It can also be applied to distributions in an envelope class.
(Show Context)

Citation Context

...assiat[13] focused on countably infinite alphabets with an envelope condition; they used an adapted strategy and gave upper and lower bounds for pointwise minimax regret. Later on Bontemps and Gassiat=-=[14]-=- worked on exponentially decreasing envelope class and provided a minimax strategy and the corresponding regret. In this paper, we introduce a straightforward and easy to implement method for large al...

Universal Compression of Envelope Classes: Tight Characterization via Poisson Sampling∗

by unknown authors , 2014
"... ar ..."
Abstract - Add to MetaCart
Abstract not found
(Show Context)

Citation Context

...up to a constant factor. For the exponential-law envelope class, defined by the envelope fi = c ⋅ e−αi where c,α > 0 they proved that2 log2 n 8α log e (1 + o(1)) ≤ R̂(Enc⋅eαi) ≤ log2 n2α log e +O(1). =-=[4]-=- improved these bounds and determined the redundancy up to the first order term and showed R̂(Enc⋅eαi) = log2 n4α log e +O(logn log logn). (2) More recently, [5] extended the arguments of [4] to find ...

unknown title

by Joint Work D. Bontemps, A. Garivier, E. Gassiat, M. Ohanessian , 2014
"... Adaptive compression over countable alphabets. S. Boucheron, ..."
Abstract - Add to MetaCart
Adaptive compression over countable alphabets. S. Boucheron,

TABLE OF CONTENTS

by unknown authors , 2014
"... Copyright Jayadev Acharya, 2014 All rights reserved. The dissertation of Jayadev Acharya is approved, and it is acceptable in quality and form for publication on microfilm and electronically: ..."
Abstract - Add to MetaCart
Copyright Jayadev Acharya, 2014 All rights reserved. The dissertation of Jayadev Acharya is approved, and it is acceptable in quality and form for publication on microfilm and electronically:
(Show Context)

Citation Context

...ers α and c is the class of distributions Λce−α· over N such that ∀i ∈ N, pi ≤ ce−αi. The redundancy of Λnce−α· was considered in [12] who proved log2 n 8α (1 + o(1)) ≤ R̂(Λnce−α·) ≤ log2 n 2α +O(1). =-=[13]-=- showed the precise growth rate of exponential envelopes and showed that R̂(Λnce−α·) = log2 n 4α (1 + o(1)). 50 An analysis of their algorithm shows that the o(1) term is of the form log logn logn , n...

Universal Compression of Envelope Classes: Tight Characterization via Poisson Sampling∗

by unknown authors , 2014
"... ar ..."
Abstract - Add to MetaCart
Abstract not found
(Show Context)

Citation Context

...up to a constant factor. For the exponential-law envelope class, defined by the envelope fi = c ⋅ e−αi where c,α > 0 they proved that2 log2 n 8α log e (1 + o(1)) ≤ R̂(Enc⋅eαi) ≤ log2 n2α log e +O(1). =-=[4]-=- improved these bounds and determined the redundancy up to the first order term and showed R̂(Enc⋅eαi) = log2 n4α log e +O(logn log logn). (2) More recently, [5] extended the arguments of [4] to find ...

1 About Adaptive Coding on Countable Alphabets §

by Dominique Bontemps, Stéphane Boucheron, Elisabeth Gassiat , 2014
"... Abstract—This paper sheds light on adaptive coding with respect to classes of memoryless sources over a countable alphabet defined by an envelope function with finite and non-decreasing hazard rate (log-concave envelope distributions). We prove that the auto-censuring (AC) code introduced by Bontemp ..."
Abstract - Add to MetaCart
Abstract—This paper sheds light on adaptive coding with respect to classes of memoryless sources over a countable alphabet defined by an envelope function with finite and non-decreasing hazard rate (log-concave envelope distributions). We prove that the auto-censuring (AC) code introduced by Bontemps (2011) is adaptive with respect to the collection of such classes. The analysis builds on the tight characterization of universal redundancy rate in terms of metric entropy by Haussler and Opper (1997) and on a careful analysis of the performance of the ACcoding algorithm. The latter relies on non-asymptotic bounds for maxima of samples from discrete distributions with finite and non-decreasing hazard rate. Index Terms—countable alphabets, redundancy, adaptive compression, minimax.
(Show Context)

Citation Context

... 9 Mar 2014 C. Roadmap This paper shows that the AC-code is adaptive over the collection of envelope classes that lie between the exponential envelope classes investigated in (Boucheron et al., 2009; =-=Bontemps, 2011-=-) and the classes of sources with finite alphabets (Theorem 2). The relevant envelopes are characterized by the fact that they have non-decreasing hazard rate (see Section III). This distributional pr...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University