LEMN improves memory networks for learning from streaming data.
problem Efficiently processing large data streams in memory-augmented neural networks.
method LEMN uses a RNN-based retention agent to learn and replace less important memory entries based on their importance and historical context.
result LEMN achieves significant improvements over existing methods in learning from streaming data.
Quantum systems with scrambling improve temporal information processing, but scaling requires exponential overhead.
problem Scalability and memory retention of quantum reservoirs in temporal information processing.
method Examined a quantum reservoir processing framework with scrambling reservoirs modeled by high-order unitary designs, analyzed in noiseless and noisy settings.
result Memory retention improves exponentially with reservoir size but worsens with reservoir iterations, requiring exponential shot overhead for scaling.
The brain optimizes memory by forgetting what's predictable, improving generalization.
problem Memory consolidation struggles with representational drift, semanticisation, and offline replay.
method Proposes predictive forgetting as a mechanism to optimize generalization by reducing complexity.
result Predictive forgetting improves information-theoretic generalization bounds on stored representations.
Paper classifies brain signals using eigenvalues for 2D and 3D educational content questions.
problem Classifying brain signals for 2D and 3D educational content questions.
method Eigenvalues of covariance matrix used as features; KNN and SVM classifiers applied.
result No significant difference in learning, memory retention, and recall between 2D and 3D educational content.
Predicting and improving player retention is crucial to the success of mobile Free-to-Play games. This paper explores the problem of rapid retention prediction in this context. Heuristic modeling approaches are introduced as a way of building simple rules for predicting short-term retention. Compared to common classifi…
PARMESAN learns from memory without parameters for fast, efficient continual learning.
problem Inflexibility in deep learning methods for continual learning.
method Transductive reasoning and memory search for parameter-free learning.
result 3-4 orders of magnitude faster than baselines, comparable performance.
This paper illustrates the similarities between the problems of customer churn and employee turnover. An example of employee turnover prediction model leveraging classical machine learning techniques is developed. Model outputs are then discussed to design \& test employee retention policies. This type of retention dis…
Improves energy efficiency of neuromorphic hardware by optimizing memory organization and encoding schemes.
problem Energy inefficiency in neuromorphic hardware, especially in digital accelerators.
method Synthesized controller and memory for different encoding schemes, introduced functional encoding for structured connectivity.
result Functional encoding offers a 58% reduction in energy for weight updates in convolutional layers.
A new memory system handles non-stationary environments by self-sizing and retaining memories.
problem Non-stationary environments where memories arrive over time and must be distinguished from noise.
method A self-sizing continual associative memory that generalizes Hopfield's network, handling adaptation and novelty.
result The memory system grows to the intrinsic memory demand of the environment and retains memories without forgetting.
In the hypothesis of rare loss events, the general expression of the policy value has been determined as a functional of the "expected frequency / loss severity" function and of the retention function. Exponential disutility has been chosen after mathematical characterization of some of its economical aspects, where fu…
A Qini-based uplift model improves retention marketing campaign performance.
problem Isolating the marketing effect of a campaign and identifying responsive customers.
method Qini-based uplift regression model using logistic regression.
result Qini-optimized uplift models improve performance and provide interpretable models.
Task-conditioned hypernetworks help neural networks learn multiple tasks without forgetting.
problem Catastrophic forgetting in neural networks when sequentially trained on multiple tasks.
method Task-conditioned hypernetworks that generate target model weights based on task identity.
result Task-conditioned hypernetworks achieve state-of-the-art performance on CL benchmarks and retain long memories.
Trellis networks improve sequence modeling performance.
problem Sequence modeling challenges.
method Temporal convolutional network with weight tying and direct input injection.
result Trellis networks outperform state-of-the-art methods on benchmarks.
FSR prevents deep nets from forgetting old tasks.
problem Catastrophic forgetting in deep neural networks.
method Logit matching on selected samples from old tasks.
result FSR outperforms previous methods in knowledge retention.
Machine learning improves learning and memory retention by optimizing study sessions.
problem Improving learning and memory retention methods for factual material.
method Large-scale randomized controlled trial with machine learning optimization of study sessions.
result Study sessions optimized with machine learning lead to 67% longer retention and 50% higher return rate.
FinMem enhances LLM trading agents with layered memory and character design.
problem Developing purpose-driven LLM agents for financial decision-making.
method Integrates layered memory and character design modules into an LLM framework.
result Significantly enhanced trading performance in financial markets.
Maximizing product use is a central goal of many businesses, which makes retention and monetization two central analytics metrics in games. Player retention may refer to various duration variables quantifying product use: total playtime or session playtime are popular research targets, and active playtime is well-suite…
This study integrates cost-sensitive and causal classification methods.
problem Improving classification model performance in business decision-making.
method A unifying evaluation framework for cost-sensitive and causal classification.
result Conventional classification is a specific case of causal classification.
Endogenous reinsurance pricing in large insurance markets
problem Endogenous reinsurance pricing in large insurance markets
method Stackelberg leader and insurer equilibrium analysis
result Characterization of insurers' equilibrium retention and Stackelberg equilibria
Machine learning models can lead to group representation disparity, affecting long-term retention.
problem Representation disparity in ML models can lead to group retention issues over time.
method Analyzed user dynamics and fairness criteria in a sequential decision-making framework.
result Representation disparity can worsen over time without proper fairness criteria.
New insights into continual learning with task similarity.
problem Challenges in learning similar tasks without interference.
method Linear teacher-student model with latent structure.
result High input feature similarity with low readout similarity is catastrophic.
Spaced repetition is a technique for efficient memorization which uses repeated, spaced review of content to improve long-term retention. Can we find the optimal reviewing schedule to maximize the benefits of spaced repetition? In this paper, we introduce a novel, flexible representation of spaced repetition using the …
Mindful active learning improves activity recognition using wearable sensors.
problem Activity recognition using wearable sensors with human cognitive and physical limitations.
method Introduces mindful active learning, a framework that considers human memory and query budget.
result EMMA framework achieves higher accuracy than traditional methods, especially with limited query budgets and weak human memory.
MACI improves LLM factuality inference with higher retention and lower time cost.
problem Ensuring factuality in LLM responses for high-stakes domains.
method Reformulated conformal inference in a multiplicative filtering setting, leveraging ensembles for more accurate factuality scores and group-conditional calibration.
result MACI achieves higher retention and lower time cost compared to baselines, preserving validity through group-conditional calibration.
Pseudo rehearsal uses non-photo-realistic images to save resources without sacrificing performance.
problem Catastrophic forgetting in neural networks when learning new tasks.
method Synthetically generate non-photo-realistic images to rehearse previous tasks.
result Non-photo-realistic images can be used for rehearsal without sacrificing performance and significantly reduce resource consumption.
CogScale benchmarks AI architectures for sequential processing.
problem Evaluating AI architectures' ability to process sequential information efficiently.
method 14 scalable synthetic tasks designed to isolate cognitive and memory abilities at different scales.
result Attention mechanisms and modern state-space models consistently maintain high performance as task difficulty scales.
New approach to continual learning prioritizes adaptation over retention.
problem Catastrophic forgetting in lifelong learning models.
method Formalized CL as an online optimization problem, introduced Transfer Efficiency, and derived a Critical Task Duration.
result Retention can hinder real-time adaptation in non-stationary environments.
The paper analyzes dynamics of momentum in high dimensions with sparse updates.
problem Theoretical analysis of momentum dynamics in high-dimensional sparse settings.
method Theoretical analysis of two models: least squares with sparse inputs and logistic regression with a rare class.
result Characterization of high-dimensional limits of momentum dynamics and phase structure.
A new AMM design reduces impermanent loss and retains more liquidity.
problem Inefficiencies in conventional AMM designs lead to liquidity loss and user engagement issues in DEXs.
method Proposes a dual-mechanism framework: a power-law invariant BMM and dynamic rebate system.
result Reduces impermanent loss by 36% and retains 3.98x more liquidity during price volatility.
The study clusters neighborhoods based on childhood vulnerability data and program retention rates.
problem Improving childhood outcomes and decision-making in early childhood development.
method Data-driven approaches combining public and private sources to visualize children's experiences and analyze program retention rates.
result Neighborhoods can be clustered based on childhood vulnerability, and certain programs have higher retention rates.
The paper uses RFM and clustering to segment bank customers.
problem Challenges in customer retention and profitable segmentation in banking.
method RFM technique and clustering algorithms applied to real data.
result Successful customer segmentation improves conversion rates.
The Open University studies student online behavior in virtual learning environments.
problem Improving retention rates in online modules.
method GUHA and Markov chain-based analysis of student activity.
result Both methods are valid for modeling student activities.
A new framework ensures model safety by retaining old model capabilities while improving new tasks.
problem Catastrophic forgetting in continual learning systems.
method Retention-centric framework with data-dependent constraints and an efficient constrained optimization algorithm.
result The method ensures that new models retain important capabilities of old models while improving new tasks.
Trimming helps in conformal prediction when it separates anomaly scores.
problem Effectiveness of trimming in conformal prediction under contamination.
method Analyse fixed-threshold trimming as a replacement of the contaminated calibration law with a retained law.
result Trimming helps when it separates anomaly scores, reducing clean-target coverage to a one-dimensional score-CDF transfer problem.
Based on a point of view that solvency and security are first, this paper considers regular-singular stochastic optimal control problem of a large insurance company facing positive transaction cost asked by reinsurer under solvency constraint. The company controls proportional reinsurance and dividend pay-out policy to…
New theory explains forgetting in learning algorithms.
problem Tendency of learning algorithms to forget past knowledge.
method Proposes a self-consistency theory of forgetting as a loss of predictive information.
result Exact Bayesian inference allows for adaptation without forgetting.
New model analyzes customer churn with tensor completion and binary data.
problem Analyzing the impact of interventions on customer churn.
method Tensorized latent factor block hazard model with 1-bit tensor completion.
result Effective categorization of interventions by similar impacts.
Unified framework for unlearning in diffusion models using KL divergence and likelihood constraints.
problem Removing undesirable data or concepts while preserving utility of pretrained models.
method Constrained optimization framework based on reverse and forward KL divergences, and likelihood constraints.
result Our KL-constrained approach achieves superior retention-unlearning tradeoffs compared to weight-based baselines.
This paper considers nonlinear regular-singular stochastic optimal control of large insurance company. The company controls the reinsurance rate and dividend payout process to maximize the expected present value of the dividend pay-outs until the time of bankruptcy. However, if the optimal dividend barrier is too low t…
Deep learning aligns GC-MS peaks for biomarker discovery.
problem Aligning retention times of GC-MS peaks across different samples.
method ChromAlignNet, a deep learning model for peak alignment.
result ChromAlignNet outperforms existing methods on complex data sets.
β-VAEs retain label info even at high compression.
problem Retaining label information in compressed representations.
method Investigation of β-VAE architectures on Binary Static MNIST and Omniglot. result β-VAEs can retain label information even at high compression.
Proposes a greedy algorithm for telecom offers to retain subscribers.
problem Maximizing revenue while preventing churn in telecom subscribers.
method Combinatorial algorithm for offer optimization under heterogeneous incentives.
result Efficient and accurate solution for large subscriber bases.
A new uplift modeling approach uses binary treatment indicators more efficiently.
problem Lack of full value utilization in binary uplift modeling.
method Design a novel transformed outcome for binary target variables.
result Our new approach outperforms traditional methods in synthetic and real-world datasets.
Paper presents AETN for efficient user modeling from mobile app usage.
problem Efficient user modeling from mobile app usage with reduced manual effort.
method AutoEncoder-coupled Transformer Network (AETN).
result AETN achieves effective user embeddings with reduced manual effort.
Graph-based approach predicts stock trends using dynamic multi-relational graphs.
problem Predicting future stock movements in complex, time-evolving stock relationships.
method Dynamic multi-relational stock graphs, stochastic diffusion process, parallel retention.
result Outperforms state-of-the-art baselines in stock trend forecasting.
A framework combining HSMM and survival analysis for lifecycle-oriented mobility analysis.
problem Understanding individual metro usage dynamics over multi-year horizons.
method A state-based lifecycle modeling framework integrating HSMM and discrete-time survival analysis.
result Identification of interpretable mobility states, transition dynamics, and state-dependent exit and re-entry processes.
Firm growth process in the developing economies is known to produce divergence in their growth path giving rise to bimodality in the size distribution. Similar bimodality has been observed in wealth distribution as well. Here, we introduce a modified kinetic exchange model which can reproduce such features. In particul…
Study forecasts U.S. bond index using deep learning, finding persistence is key.
problem Forecasting U.S. aggregate bond index with deep learning methods.
method Constructed a stationary but maximally persistent representation of the bond index, evaluated using MLPs and CNNs.
result Deep learning models outperform traditional methods in short-horizon forecasting of bond indices.