Prediction with a Short Memory
This provides a theoretical foundation for efficient prediction in sequential data, demonstrating that short memory suffices for many cases, which is incremental but clarifies limits on long-range dependency needs.
The paper tackles the problem of predicting future observations from sequences, showing that for distributions with bounded mutual information I, a simple Markov model using only the most recent I/ε observations achieves expected KL error ε, matching the optimal predictor. For Hidden Markov Models with n hidden states, this reduces to using windows of length O(log n/ε) with sample complexity d^{Θ(log n/ε)}.
We consider the problem of predicting the next observation given a sequence of past observations, and consider the extent to which accurate prediction requires complex algorithms that explicitly leverage long-range dependencies. Perhaps surprisingly, our positive results show that for a broad class of sequences, there is an algorithm that predicts well on average, and bases its predictions only on the most recent few observation together with a set of simple summary statistics of the past observations. Specifically, we show that for any distribution over observations, if the mutual information between past observations and future observations is upper bounded by $I$, then a simple Markov model over the most recent $I/ε$ observations obtains expected KL error $ε$---and hence $\ell_1$ error $\sqrtε$---with respect to the optimal predictor that has access to the entire past and knows the data generating distribution. For a Hidden Markov Model with $n$ hidden states, $I$ is bounded by $\log n$, a quantity that does not depend on the mixing time, and we show that the trivial prediction algorithm based on the empirical frequencies of length $O(\log n/ε)$ windows of observations achieves this error, provided the length of the sequence is $d^{Ω(\log n/ε)}$, where $d$ is the size of the observation alphabet. We also establish that this result cannot be improved upon, even for the class of HMMs, in the following two senses: First, for HMMs with $n$ hidden states, a window length of $\log n/ε$ is information-theoretically necessary to achieve expected $\ell_1$ error $\sqrtε$. Second, the $d^{Θ(\log n/ε)}$ samples required to estimate the Markov model for an observation alphabet of size $d$ is necessary for any computationally tractable learning algorithm, assuming the hardness of strongly refuting a certain class of CSPs.