Learning what to remember
We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory. We introduce a mathematical model based on the online learning framework, in which the learner measures itself against a collection of experts that are also memory-constrained and that reflect different policies for what to remember. Interspersed with the stream of facts are occasional questions, and on each of these the learner incurs a loss if it has not remembered the corresponding fact. Its goal is to do almost as well as the best expert in hindsight, while using roughly the same amount of memory. We identify difficulties with using the multiplicative weights update algorithm in this memory-constrained scenario, and design an alternative scheme whose regret guarantees are close to the best possible.
Code (0)
등록된 구현이 없습니다.
Tasks
Lifelong learningSimilar Papers 제목 키워드 기반
AdaMem: Learning What to Remember for Personalized Long-Horizon LLM Agents
Long-term memory systems for Large Language Model (LLM) agents typically try to \emph{remember everything}, extracting memories uniformly to retain as many facts as possible. In production, however, inference cost and fi…
State Gradients for RNN Memory Analysis
We present a framework for analyzing what the state in RNNs remembers from its input embeddings. Our approach is inspired by backpropagation, in the sense that we compute the gradients of the states with respect to the i…
Shared memories driven by the intrinsic memorability of items
When we experience an event, it feels like our previous experiences, our interpretations of that event (e.g., aesthetics, emotions), and our current state will determine how we will remember it. However, recent work has …
The Right to Be Remembered: Preserving Maximally Truthful Digital Memory in the Age of AI
Since the rapid expansion of large language models (LLMs), people have begun to rely on them for information retrieval. While traditional search engines display ranked lists of sources shaped by search engine optimizatio…
Information RetrievalNon-parametric Memory for Spatio-Temporal Segmentation of Construction Zones for Self-Driving
In this paper, we introduce a non-parametric memory representation for spatio-temporal segmentation that captures the local space and time around an autonomous vehicle (AV). Our representation has three important propert…