• Corpus ID: 239998142

Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio

@article{Orabona2021TightCA,
  title={Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio},
  author={Francesco Orabona and Kwang-Sung Jun},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.14099}
}
A classic problem in statistics is the estimation of the expectation of random variables from samples. This gives rise to the tightly connected problems of deriving concentration inequalities and confidence sequences, that is confidence intervals that hold uniformly over time. Jun and Orabona [COLT’19] have shown how to easily convert the regret guarantee of an online betting algorithm into a time-uniform concentration inequality. In this paper, we show that we can go even further: We show that… 
[PDF] Semantic Reader
9 Citations
Highly Influential Citations
2
Background Citations
7
Methods Citations
3
Results Citations
1

Figures from this paper

9 Citations

On Confidence Sequences for Bounded Random Processes via Universal Gambling Strategies

A new algorithm based on a mixture of lower bounds, which closely approximates the performance of Cover’s universal portfolio with only constant per-round time complexity is proposed.

Tighter PAC-Bayes Bounds Through Coin-Betting

This paper derives the first PAC-Bayes concentration inequality based on the coin-betting approach that holds simultaneously for all sample sizes and demonstrates its tightness showing that byrelaxing it the authors obtain a number of previous results in a closed form including Bernoulli-KL and empirical Bernstein inequalities.

A nonparametric extension of randomized response for private confidence sets

This work derives methods for performing nonparametric, nonasymptotic statistical inference for population means under the constraint of local differential privacy (LDP). Given bounded observations…

Anytime-Valid Confidence Sequences in an Enterprise A/B Testing Platform

An experimentation service on the Adobe Experience Platform based on anytime-valid confidence sequences is released, allowing for continuous monitoring of the A/B test and data-dependent stopping and showing the desirable properties of using anytime- valid methods instead of traditional approaches.

Parameter-free Regret in High Probability with Heavy Tails

We present new algorithms for online convex optimization over unbounded domains that obtain parameter-free regret in high-probability given access only to potentially heavy-tailed subgradient…

Game-theoretic statistics and safe anytime-valid inference

: Safe anytime-valid inference (SAVI) provides measures of statistical evidence and certainty—e-processes for testing and confidence sequences for estimation—that remain valid at all stopping times,…

Time-uniform central limit theory with applications to anytime-valid causal inference A Proofs of the main results

This work introduces time-uniform analogues of confidence intervals based on the central limit theorem (CLT). Our methods take the form of confidence sequences (CS) — sequences of confidence intervals…

Post-selection inference for e-value based confidence intervals

Suppose that one can construct a valid (1 − 𝛿 ) -CI for each of 𝐾 parameters of potential interest. If a data analyst uses an arbitrary data-dependent criterion to select some subset 𝑆 of…

Safe Testing

Sharing Fisherian, Neymanian and Jeffreys-Bayesian interpretations, S-values and safe tests may provide a methodology acceptable to adherents of all three schools.

References

SHOWING 1-10 OF 70 REFERENCES

Time-uniform, nonparametric, nonasymptotic confidence sequences

A confidence sequence is a sequence of confidence intervals that is uniformly valid over an unbounded time horizon. Our work develops confidence sequences whose widths go to zero, with nonasymptotic…

Prediction, learning, and games

This chapter discusses prediction with expert advice, efficient forecasters for large classes of experts, and randomized prediction for specific losses.

Parameter-free Online Convex Optimization with Sub-Exponential Noise

It is shown that it is possible to go around the lower bound by allowing the observed subgradients to be unbounded via stochastic noise, and a novel parameter-free OCO algorithm for Banach space, which is called BANCO, achieves the optimal regret rate.

Estimating means of bounded random variables by betting

A general approach for deriving concentration bounds, that can be seen as a generalization and improvement of the celebrated Chernoff method, based on a class of composite nonnegative martingales, with strong connections to testing by betting and the method of mixtures is presented.

Binomial Confidence Intervals

Abstract For X with Binomial (n, p) distribution, Section 1 gives a one-page table of .95 and .99 confidence intervals for p, for n = 1, 2, …, 30. This interval is equivariant under X → n − X and p →…

THE USE OF CONFIDENCE OR FIDUCIAL LIMITS ILLUSTRATED IN THE CASE OF THE BINOMIAL

Aggregating strategies

  • V. Vovk
  • Computer Science
    COLT '90
  • 1990

Universal Portfolios

We exhibit an algorithm for portfolio selection that asymptotically outperforms the best stock in the market. Let x i = (x i1 ; x i2 ; : : : ; x im) t denote the performance of the stock market on…

Universal portfolios with side information

This is an individual sequence result which shows the difference between the exponential growth wealth of the best state-constant rebalanced portfolio and the universal portfolio with side information is uniformly less than (d/(2n))log (n+1)+(k/n)log 2 for every stock market and side-information sequence and for all time n.

Universal gambling schemes and the complexity measures of Kolmogorov and Chaitin

  • Technical Report 12,
  • 1974
...