Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth

• URL: http://arxiv.org/abs/2604.00067v1
• Date: Tue, 31 Mar 2026 12:04:11 GMT
• Title: Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth
• Abstract summary: An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget.<n>We propose a framework in which memory is not a parameter vector but a process: a Diffusion Bridge on a replay interval.<n>The framework provides a fully analytical Ising model'' of continual learning in which the mechanism, rate, and form of forgetting can be studied with mathematical precision.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge Diffusion on a replay interval $[0,1]$, whose terminal marginal encodes the present and whose intermediate marginals encode the past. New experience is incorporated via a three-step \emph{Compress--Add--Smooth} (CAS) recursion. We test the framework on the class of models with marginal probability densities modeled via Gaussian mixtures of fixed number of components~$K$ in $d$ dimensions; temporal complexity is controlled by a fixed number~$L$ of piecewise-linear protocol segments whose nodes store Gaussian-mixture states. The entire recursion costs $O(LKd^2)$ flops per day -- no backpropagation, no stored data, no neural networks -- making it viable for controller-light hardware. Forgetting in this framework arises not from parameter interference but from lossy temporal compression: the re-approximation of a finer protocol by a coarser one under a fixed segment budget. We find that the retention half-life scales linearly as $a_{1/2}\approx c\,L$ with a constant $c>1$ that depends on the dynamics but not on the mixture complexity~$K$, the dimension~$d$, or the geometry of the target family. The constant~$c$ admits an information-theoretic interpretation analogous to the Shannon channel capacity. The stochastic process underlying the bridge provides temporally coherent ``movie'' replay -- compressed narratives of the agent's history, demonstrated visually on an MNIST latent-space illustration. The framework provides a fully analytical ``Ising model'' of continual learning in which the mechanism, rate, and form of forgetting can be studied with mathematical precision.

Related papers

• Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes [70.61868608402723]
  We introduce $textbfSelf-Correcting Coupled Markov Jump Processes (SC-CMJP)<n>In conjunction with SC-CMJP, we introduce $textttCO_texttt2textttJump$, a novel training-free single-pass sampler for joint multimodal geneneration.<n>For training and evaluation purposes, we have created and will release three large-scale joint multimodal generation corpora.
  arXiv  Detail & Related papers  (2026-07-14T18:39:29Z)
• DMF: A Deterministic Memory Framework for Conversational AI Agents [0.0]
  We present the Deterministic Memory Framework (DMF), a CPU-first approach that replaces generative memory compression with a fully deterministic pipeline.<n>DMF assigns each conversational interaction a Survival Score $$ computed from deterministic content signals, conversational cues, and structured provenance, combined through a logistic projection.<n>Experiments are conducted on a purpose-built benchmark using the LoCoMo and LongMemEval datasets.
  arXiv  Detail & Related papers  (2026-06-02T10:41:28Z)
• Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent [39.805192541498634]
  We study nonstationary linear computation (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-varying parameter.<n>We propose a new algorithm for nonstationary GLBs that utilize discounted online mirror descent (DOMD) for parameter estimation, thereby incurring only $O(1)$ for memory costs per round.
  arXiv  Detail & Related papers  (2026-05-25T08:40:32Z)
• Persistent Memory Through Triple-Loop Consolidation in a Non-Gradient Dissipative Cognitive Architecture [0.0]
  We introduce Deep Memory, a non-gradient persistent memory mechanism operating through a triple-loop consolidation cycle.<n>We demonstrate that discrete expert routing via Mixture-of-Experts (MoE) gating is a causal prerequisite for DM.<n>These results establish DM as a falsifiable mechanism for persistent memory in non-gradient cognitive systems, with functional parallels to hippocampal consolidation.
  arXiv  Detail & Related papers  (2026-03-28T08:29:48Z)
• Phase Diagrams of Information Backflow: Unifying Entanglement Revivals and Entropy Overshoots in Minimal Non-Markovian Models [0.0]
  Memory effects in non-Markovian dynamics are often diagnosed either via quantum-correlation revivals or via non-monotonic classical information measures.<n>We propose an information-backflow phase-diagram approach that places emphquantum entanglement revivals and emphclassical entropy overshoots.<n>We quantify non-monotonicity by the entropy overshoot $H$ and KL-based diagnostics on the probability simplex.
  arXiv  Detail & Related papers  (2026-01-25T02:58:47Z)
• One-Shot Federated Ridge Regression: Exact Recovery via Sufficient Statistic Aggregation [0.7106986689736825]
  Federated ridge regression is a distributed equilibrium problem where each client computes local sufficient statistics and transmits them once.<n>We establish differential privacy guarantees where noise is injected once per client, eliminating the composition penalty that degrades privacy in multi-round protocols.<n>Experiments on synthetic heterogeneous regression demonstrate that one-shot fusion matches FedAvg accuracy while requiring up to $38times$ less communication.
  arXiv  Detail & Related papers  (2026-01-13T04:47:22Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• From Continual Learning to SGD and Back: Better Rates for Continual Linear Models [50.11453013647086]
  We analyze the forgetting, i.e., loss on previously seen tasks, after $k$ iterations.<n>We develop novel last-iterate upper bounds in the realizable least squares setup.<n>We prove for the first time that randomization alone, with no task repetition, can prevent catastrophic in sufficiently long task sequences.
  arXiv  Detail & Related papers  (2025-04-06T18:39:45Z)
• Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs [56.237917407785545]
  We consider the problem of learning an $varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.
  arXiv  Detail & Related papers  (2024-05-10T09:58:47Z)
• Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition [71.33787410075577]
  We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses. We propose a new algorithm that attains an $widetildeO(dsqrtHS3K + sqrtHSAK)$ regret with high probability.
  arXiv  Detail & Related papers  (2024-03-07T15:03:50Z)
• Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning [78.30395044401321]
  We develop a novel model-based approach to reinforcement learning (MBRL) It relaxes the assumptions on the target transition model to belong to a generic family of mixture models. It can achieve up-to 50 percent reduction in wall clock time in some continuous control environments.
  arXiv  Detail & Related papers  (2022-06-02T17:27:49Z)
• An Improved Analysis of Gradient Tracking for Decentralized Machine Learning [34.144764431505486]
  We consider decentralized machine learning over a network where the training data is distributed across $n$ agents. The agent's common goal is to find a model that minimizes the average of all local loss functions. We improve the dependency on $p$ from $mathcalO(p-1)$ to $mathcalO(p-1)$ in the noiseless case.
  arXiv  Detail & Related papers  (2022-02-08T12:58:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.