A new lifelong online learning framework combining current and accumulated knowledge.
problem Continuous learning over tasks with limited data and unknown number of instances.
method Interactive learning algorithm combining current task information and accumulated knowledge.
result Algorithm can benefit from small cumulative error even with few interactions.
An agent explores indefinitely in an environment with unlimited rewards.
problem Balancing exploration and exploitation in environments with unlimited rewards.
method Simple example of an environment with unbounded rewards and optimal agent behavior.
result An optimal agent always explores to maximize rewards, regardless of accumulated knowledge.
A new theory quantifies how societies accumulate and diversify their knowledge.
problem Lack of a unified quantitative formalism for understanding societal knowledge accumulation.
method Combines analytical, numerical, and empirical approaches to quantify and predict societal diversification.
result Measurable quantities to predict future societal developments.
Machines, not humans, are the world's dominant knowledge accumulators but humans remain the dominant decision makers. Interpreting and disseminating the knowledge accumulated by machines requires expertise, time, and is prone to failure. The problem of how best to convey accumulated knowledge from computers to humans i…
To survive in the dynamically-evolving world, we accumulate knowledge and improve our skills based on experience. In the process, gaining new knowledge does not disrupt our vigilance to external stimuli. In other words, our learning process is 'accumulative' and 'online' without interruption. However, despite the recen…
In many large-scale machine learning applications, data are accumulated with time, and thus, an appropriate model should be able to update in an online paradigm. Moreover, as the whole data volume is unknown when constructing the model, it is desired to scan each data item only once with a storage independent with the …
Framework evaluates the impact of prior knowledge in deep learning models.
problem Mitigating data-driven model shortcomings like data dependence and generalization ability.
method Model-agnostic framework inspired by interpretable machine learning, assessing data volume and estimation range effects.
result Complex relationship between data and knowledge, including dependence, synergistic, and substitution effects.
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming…
A machine learning model for PMD compensation in dual-polarization systems.
problem Compensating for polarization-mode dispersion (PMD) in dual-polarization systems.
method Model-based machine learning approach using the split-step Fourier method for the Manakov-PMD equation.
result The model converges to within 1% of peak dB performance after 428 iterations, achieving a 0.30 dB reduction in effective signal-to-noise ratio compared to PMD-free case.
Few-shot network compression improves accuracy with minimal data.
problem High estimation errors from original network during inference.
method Cross distillation, layer-wise knowledge distillation approach.
result Cross distillation significantly improves student network's accuracy with few training instances.
New method analyzes accumulation precision in deep learning networks.
problem Lack of precision analysis for accumulation in deep learning training.
method Statistical approach to analyze partial sum accumulations and derive equations for minimum required bits.
result Reduced accumulation precision can lead to loss of information and degraded network quality.
NAK model predicts student grades by focusing on relevant past courses.
problem Accurately predicting future course grades for students.
method NAK model learns attention weights to focus on relevant past courses.
result NAK model outperforms CKRM and other methods in predicting grades.
Proposes MEDIC to improve incremental learning by preventing forgetting and intransigence.
problem Challenges of forgetting old knowledge and intransigence on new knowledge in incremental learning.
method Maximum Entropy Regularizer (MER) and DropOut Sampling (DOS) to penalize uncertain knowledge and reduce class imbalance.
result Proposed method 'MEDIC' outperforms state-of-the-art algorithms in accuracy, forgetting, and intransigence.
Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and app…
We look at a collection of conjectures with the unifying message that smaller social systems, tend to be less complex and can be aligned better, towards fulfilling their intended objectives. We touch upon a framework, referred to as the four pronged approach that can aid the analysis of social systems. The four prongs …
This paper reviews deep learning and knowledge-based methods for molecular design.
problem Optimizing molecular properties for scientific advances and process performance.
method Survey of deep learning and knowledge-based methods for molecular design.
result Deep learning models show promise in overcoming computational challenges.
Paper proposes methods to discover causal models with unobserved variables.
problem Discovering causal relationships in data with unobserved variables.
method Two methods leveraging prior knowledge for causal discovery in CAM-UV models.
result Accuracy of causal discovery improves with more prior knowledge.
Accumulated stock returns exhibit tempered skew t-distribution.
problem Analyzing the distribution of stock returns over multiple days.
method Employing a tempered skew t-distribution model.
result Tempered skew t-distribution fits the distribution of accumulated stock returns well.
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a way which captures the common structure across learned tasks, while allowing the…
Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The posterior can go beyond the mean field approximation and yields good uncertainty on the …
Financial investment returns lead to growing wealth inequality.
problem Recent rise in wealth inequality in active financial markets.
method Minimalist modelling strategy combining financial markets, wealth accumulation, and compound interest.
result Accumulated financial investment returns cause ever-increasing wealth concentration and inequality.
New IDS algorithm refines parameter norm bounds for better bandit performance.
problem Frequentist IDS requires tight norm bounds, which are often unavailable in practice.
method Iteratively refines a high-probability upper bound on true parameter norm using data.
result Regret bounds independent of assumed parameter norm, outperforming state-of-the-art algorithms.
L2SC improves spectral clustering performance by selectively transferring knowledge across tasks.
problem L2SC tackles the challenge of incorporating new spectral clustering tasks without relearning all previous tasks.
method L2SC uses an orthogonal basis library and feature embedding library to selectively transfer knowledge from previously learned tasks to new tasks.
result L2SC outperforms state-of-the-art spectral clustering algorithms on real-world benchmark datasets.
Survey tackles continual learning in classification tasks to prevent forgetting.
problem Prevent catastrophic forgetting in neural networks across multiple tasks.
method Taxonomy, stability-plasticity trade-off framework, comprehensive comparison of methods.
result Empirical evaluation of continual learning methods on various benchmarks.
Unfolding paths in Outer space accumulate on a simplex, not converge.
problem Understanding accumulation points in Outer space.
method Constructing an unfolding path in Outer space.
result Unfolding paths accumulate on a 1-simplex, not converge.
New data accumulation prevents model collapse in generative models.
problem Model collapse in generative models trained on their own outputs.
method Empirical study of language models, diffusion models, and variational autoencoders; analytically tractable framework for linear models.
result Accumulating synthetic data alongside real data avoids model collapse, preventing performance degradation.
The paper analyzes how synthetic data training degrades diffusion models, providing bounds and characterizing different drift regimes.
problem The degradation of performance in diffusion models trained on synthetic data.
method Theoretical analysis of score-based diffusion models, focusing on the accumulated divergence between generated and target distributions.
result Upper and lower bounds on the accumulated divergence, providing the first lower bound for diffusion models.
Study of historic stock returns distributions, highlighting asymmetry and outliers.
problem Understanding the asymmetry in accumulated gains and losses in stock returns over time.
method Analyzing decades-long historic distributions of S&P500 returns, comparing gains and losses, using statistical U-tests and fitting log-log scale linearly.
result The mean of de-trended distributions increases linearly with the number of days of accumulation, and the overall skew is negative, indicating heavier tails of losses.
ASLA learns atomic structures using neural networks and reinforcement learning.
problem Designing materials and drugs with desired properties.
method Atomistic structure learning algorithm (ASLA) using a convolutional neural network and reinforcement learning.
result ASLA can predict optimal structural arrangements of atoms for various target properties.
GenIE extracts structured text with fewer errors and more entities.
problem Closed information extraction with errors and limited entities.
method End-to-end autoregressive generation with bi-level constraints.
result State-of-the-art performance on closed information extraction.
Model of capital accumulation in a complex exchange space.
problem Capital accumulation dynamics in heterogeneous producer-consumer systems.
method Statistical field theory approach to analyze interactions and dynamics.
result Capital accumulation and agent position in the exchange space are correlated.
Accumulator module improves reinforcement learning by delaying decisions based on evidence.
problem Incomplete information, limited sensing, and stochastic environments lead to risky decisions.
method Integrates evidence for each action, delays action until confident, using dynamic competition.
result Accumulator module outperforms traditional reinforcement learning methods in a guessing game.
In this paper, finite type domains with hyperbolic orbit accumulation points are studied. We prove, in case of C2, it has to be a (global) pseudoconvex domain, after an assumption of boundary regularity. Moreover, one of the applications will realize the classification of domains within this class, precisel…
New study shows MLE can avoid model collapse with gradual synthetic data addition.
problem Model collapse in generative models trained on synthetic data.
method Theoretical study of maximum likelihood estimation (MLE) under iterative training with accumulating synthetic data.
result Non-asymptotic bounds show MLE can avoid model collapse even as real data fraction vanishes.
This paper presents a numerical model to solve the problem of cash accumulation strategies for products with an unknown future price, like assets. Stock prices are modeled by a discretized Wiener Process, and by the means of ordinary integrals this Wiener Process will be exactly matched at a preset terminal time. Three…
Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue . They are based on the statistical analysis of accumulated and moving window data subsets with construction of a kurtosis-skewness diagram. This approach was applied to the data gat…
CLA improves investment accuracy by leveraging past knowledge.
problem Improving investment decisions through past knowledge integration.
method CLA uses an explicit memory structure and FFNN base model, incorporating change points and contextual similarity.
result CLA significantly outperforms FFNN base models in expected return forecasting.
Imaging neuroscience links brain activation maps to behavior and cognition via correlational studies. Due to the nature of the individual experiments, based on eliciting neural response from a small number of stimuli, this link is incomplete, and unidirectional from the causal point of view. To come to conclusions on t…
Experience replay helps neural networks learn new tasks without forgetting old knowledge.
problem Catastrophic forgetting in neural networks trained on non-stationary data.
method Experience replay buffers with a mixture of on- and off-policy learning.
result Experience replay can learn new tasks quickly and reduce catastrophic forgetting.
Analyzes multi-day stock returns, showing linear volatility and mean dependence.
problem Linear dependence of volatility and mean in accumulated stock returns.
method Modified Jones-Faddy skew t-distribution analysis.
result Linear dependence of volatility and mean on the number of days of accumulation.
ReCAP adapts to dynamic financial markets by segmenting and combining policy vectors.
problem Inefficient traditional PM approaches in non-stationary financial markets.
method Integrates continual learning into PM, segmenting regimes and adapting policies.
result Consistently outperforms baselines in real-world financial datasets.
In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-disti…
Improved statistical computation through efficient matrix sampling.
problem Reducing computational cost in large-scale statistical methods.
method Accumulative sub-sampling method to improve statistical efficiency.
result Effective matrix size control improves computational efficiency.
DANCE method improves large-scale learning efficiency via accumulating sample strategy.
problem Efficiently solving large-scale empirical risk minimization problems.
method Distributed Accumulated Newton Conjugate gradient (DANCE) method with multistage approach.
result The method achieves satisfactory statistical accuracy with fewer passes over data.
Subspace clustering is the unsupervised grouping of points lying near a union of low-dimensional linear subspaces. Algorithms based directly on geometric properties of such data tend to either provide poor empirical performance, lack theoretical guarantees, or depend heavily on their initialization. We present a novel …
Unified framework models neural decision-making, improving accuracy.
problem Limitations in modeling neural activity during decision-making.
method Unifying framework based on state-space models with scalable inference.
result Two-dimensional accumulator better captures neural responses.
We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates th…
New method speeds up lifelong learning of complex tasks.
problem Catastrophic forgetting in lifelong learning.
method Directly trains lifelong function approximators via policy gradients.
result Faster convergence and better policies achieved.