The Elusive Present: Hidden Past and Future Dependency and Why We Build Models
Modeling a temporal process as if it is Markovian assumes the present encodes all of the process's history. When this occurs, the present captures all of the dependency between past and future. We recently showed that if one randomly samples in the space of structured processes, this is almost never the case. So, how does the Markov failure come about? That is, how do individual measurements fail to encode the past? And, how many are needed to capture dependencies between the past and future? Here, we investigate how much information can be shared between the past and future, but not be reflected in the present. We quantify this elusive information, give explicit calculational methods, and draw out the consequences. The most important of which is that when the present hides past-future dependency we must move beyond sequence-based statistics and build state-based models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Dependency Parsing: Past, Present, and Future
Tractable Offline Learning of Regular Decision Processes
This work studies offline Reinforcement Learning (RL) in a class of non-Markovian environments called Regular Decision Processes (RDPs). In RDPs, the unknown dependency of future observations and rewards from the past in…
Offline RLReinforcement Learning (RL)Global Optimality in Neural Network Training
The past few years have seen a dramatic increase in the performance of recognition systems thanks to the introduction of deep networks for representation learning. However, the mathematical reasons for this success remai…
Representation LearningPalm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023
We present Palm, a solution to the Long-Term Action Anticipation (LTA) task utilizing vision-language and large language models. Given an input video with annotated action periods, the LTA task aims to predict possible f…
Action AnticipationImage CaptioningLanguage ModelingLanguage Modelling+2Rethinking the long-range dependency in Mamba/SSM and transformer models
Long-range dependency is one of the most desired properties of recent sequence models such as state-space models (particularly Mamba) and transformer models. New model architectures are being actively developed and bench…