Dynamic information balancing reduces catastrophic forgetting in modular neural networks.
problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Dynamic Information Balancing (DIB) using reinforcement learning to adaptively route inputs based on module information load.
result DIB combined with EWC regularization outperforms models with similar capacity and EWC regularization.
WiGS improves active learning for regression by dynamically selecting informative samples.
problem Reducing labeling costs in regression tasks.
method Formulated as a reinforcement learning problem, WiGS adapts the exploration-investigation balance.
result WiGS outperforms static methods in accuracy and labeling efficiency, especially in irregular data density.
DADI framework dynamically discovers fair information using reinforcement learning.
problem Discovering fair information from third-party features with unknown objectives.
method Adversarial reinforcement learning agent that balances accuracy and fairness.
result Achieves group fairness by rewarding the agent with the adversary's loss.
Surprise describes a range of phenomena from unexpected events to behavioral responses. We propose a measure of surprise and use it for surprise-driven learning. Our surprise measure takes into account data likelihood as well as the degree of commitment to a belief via the entropy of the belief distribution. We find th…
Controller seeks informative system observations to predict nonlinear dynamics.
problem Predicting nonlinear dynamics with uncertain parameters.
method Expected free energy minimization for balancing goal state and informative observations.
result Controller improves performance in uncertain parameter scenarios.
Study compares empirical systemic risk with balance sheet risk in interbank networks.
problem Disentangling balance sheet risk from network effects in systemic risk.
method Generalised DebtRank dynamics and maximum-entropy approach to compare observed and expected systemic risk.
result Systemic risk levels are compatible but differ significantly during turbulent times.
Dynamic treatment effects estimated over time using covariate balancing.
problem Estimating treatment effects in panel data with dynamic treatments.
method Dynamic covariate balancing with potential local projections.
result Established inferential guarantees for the proposed method.
Unified formula for training dynamics of linear networks combining lazy and balanced regimes.
problem Training dynamics of linear networks in two distinct setups: lazy and balanced/active.
method Unified formula for the evolution of the learned matrix, combining lazy and balanced regimes.
result Unified formula allows for rapid convergence and low rank bias, proving a complete phase diagram.
We derive a class of macroscopic differential equations that describe collective adaptation, starting from a discrete-time stochastic microscopic model. The behavior of each agent is a dynamic balance between adaptation that locally achieves the best action and memory loss that leads to randomized behavior. We show tha…
Batch Thompson Sampling reduces exploration-exploitation trade-off in online decision making.
problem Balancing exploration and exploitation in online decision making.
method Introducing a batch Thompson Sampling framework for stochastic multi-arm bandit and linear contextual bandit problems.
result Achieves asymptotic regret bound with O(logT) batch queries, significantly reducing interactions. Two heuristics solve dynamic multiple travelling salesmen problems.
problem Dynamic routing with unknown customers.
method Balanced dynamic closest vehicle heuristic and balanced dynamic assignment vehicle heuristic.
result Continuous approximation models for strategic dynamic routing.
Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.
problem Balancing exploration and exploitation in active learning for unknown functions.
method Develops BHEEM, a Bayesian hierarchical approach with approximate Bayesian computation for sampling trade-off parameters.
result BHEEM achieves at least 21% and 11% improvement over pure exploration and exploitation strategies respectively.
SGD in DLNs reveals feature learning dynamics.
problem Understanding SGD dynamics in DLNs during saddle-to-saddle training.
method Stochastic Langevin dynamics with anisotropic, state-dependent noise; one-dimensional per-mode SDEs; Boltzmann distribution approximation.
result SGD noise encodes feature learning progression but does not alter saddle-to-saddle dynamics.
ADAPT method controls balance between sparse generator and discriminator in GANs.
problem High computational complexity in GANs training.
method Balanced Dynamic Sparse Training (ADAPT) method.
result ADAPT method achieves a good trade-off between performance and computational cost.
Paper proposes D3M to improve anti-spoofing detection by balancing loss function and using complementary features.
problem Improving automatic speaker verification systems against high-quality playback attacks.
method D3M uses a balanced focal loss function to dynamically scale loss based on sample traits, and combines three feature types for robust detection.
result D3M systems outperform conventional methods significantly, achieving min-tDCF of 0.0124 and EER of 0.55%.
Employing data on the assessed value of land in 1983 -- 2005 Japan, we investigate the dynamical behavior in the high scale region of non-equilibrium systems. From the detailed quasi-balance and Gibrat's law, we derive a relation between the change of Pareto index and a symmetry in the detailed quasi-balance. The relat…
HCLM framework uses entropy regularization for open learning systems.
problem Real-world AI challenges and limitations of deep learning.
method Dynamical and information-theoretic framework with entropy regularization.
result Geometric entropy surrogates, especially log-determinant covariance entropy, induce stronger and more stable information forces.
In \cite{D3}, Donaldson defines a dynamical system on the space of Fubini-Study metrics on a polarized compact Kähler manifold. Sano proved that if there exists a balanced metric for the polarization, then this dynamical system always converges to the balanced metric (\cite{S}). In \cite{DKLR}, Douglas, et. al., conjec…
Physics-guided reinforcement learning optimizes swimming in turbulent flows.
problem Optimizing swimming efforts to maintain proximity in turbulent environments.
method Physics-informed actor-physicist reinforcement learning algorithm.
result Physics-informed reinforcement learning outperforms standard methods in turbulent flow control.
An active learning approach reduces AoI violation in vehicular networks.
problem Dynamic nature of vehicular networks makes resource allocation challenging.
method Gaussian process regression (GPR) for online decentralized active learning.
result Significant improvement in AoI violation probability with at least 50% reduction.
Paper explores balancing market dynamics and interpretable forecasting models for energy prices.
problem Tackles the challenge of accurately predicting mFRR price and understanding market dynamics.
method Compares XGBoost and EBM for forecasting mFRR activation price in the balancing market.
result EBM provides comparable forecasting accuracy to XGBoost but with higher interpretability.
New method learns adaptive exploration strategies for dynamic tasks.
problem Learning effective exploration strategies in changing environments.
method Informed policy regularization to reduce sample complexity of RNN-based policies.
result Method learns efficient exploration strategies balancing information gathering and reward maximization.
This work is devoted to modelling and identification of the dynamics of the inter-sectoral balance of a macroeconomic system. An approach to the problem of specification and identification of a weakly formalized dynamical system is developed. A matching procedure for parameters of a linear stationary Cauchy problem wit…
We develop an efficient sampling method by simulating Langevin dynamics with an artificial force rather than a natural force by using the gradient of the potential energy. The standard technique for sampling following the predetermined distribution such as the Gibbs-Boltzmann one is performed under the detailed balance…
MTAdam optimizes multiple loss terms in neural models, balancing gradients dynamically.
problem Balancing multiple loss terms in neural model training is challenging and computationally demanding.
method Generalized Adam algorithm that computes separate derivatives and balances gradients across layers dynamically.
result Training with MTAdam leads to faster recovery from suboptimal initial loss weighting and matches conventional training outcomes.
An agent-based model for firms' dynamics is developed. The model consists of firm agents with identical characteristic parameters and a bank agent. Dynamics of those agents is described by their balance sheets. Each firm tries to maximize its expected profit with possible risks in market. Infinite growth of a firm dire…
TV-SurvCaus improves causal inference for dynamic treatments in survival analysis.
problem Estimating causal effects of time-varying treatments on survival outcomes.
method Representation balancing techniques extended to time-varying treatment regimes with survival outcomes.
result TV-SurvCaus outperforms existing methods in estimating individualized treatment effects with time-varying covariates and treatments.
Study finds significant BTC co-movements with equity markets, highlighting dynamic risk management needs.
problem Understanding the impact of corporate Bitcoin holdings on equity markets.
method Dataset of 39 firms, daily returns analysis, Pearson correlations, single factor model regressions, transfer entropy.
result BTC has a significant positive beta with equity markets, with BTC as the dominant information driver.
ADVISOR dynamically balances imitation and reinforcement learning to overcome the imitation gap.
problem The gap between imitation learning and reinforcement learning when teaching agents have privileged information.
method Adaptive Insubordination (ADVISOR) dynamically weights imitation and reward-based reinforcement learning losses.
result On-the-fly switching with ADVISOR outperforms pure imitation, pure reinforcement learning, and their combinations.
Cross-balancing improves causal inference by balancing features with outcome data.
problem Balancing features for valid causal inference when outcome data is available.
method Cross-balancing using sample splitting to separate feature construction and weight estimation errors.
result Cross-balancing produces consistent, asymptotically normal, and efficient estimators under mild conditions.
New method predicts graph structure changes over time.
problem Existing graph prediction methods assume static vertices, limiting their applicability.
method Combines time series prediction with adapted FBA for growing graphs.
result Efficacy demonstrated on synthetic and real datasets.
Study examines how balancing methods affect model behavior in imbalanced classification problems.
problem Impact of balancing methods on model behavior in imbalanced classification problems.
method Used Explainable Artificial Intelligence tools (variable importance method, partial dependence profile, accumulated local effects) to compare model behavior before and after balancing.
result Significant changes in model behavior due to balancing methods, leading to biased models.
LSB is a new MCMC method for discrete spaces that reduces target evaluations.
problem Sampling in discrete domains with high efficiency and adaptability.
method Local self-balancing proposals, mutual information objective, self-balancing learning.
result LSB converges with fewer target evaluations compared to existing methods.
Flashback Learning balances model stability and plasticity in continual learning.
problem Balancing model stability and plasticity in continual learning.
method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.
result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.
The paper proposes Tier Balancing for dynamic fairness in decision-making.
problem Achieving long-term fairness in decision-making processes.
method Causal modeling with DAGs to investigate dynamic fairness.
result Tier Balancing is a more natural approach to achieve long-term fairness, capturing latent causal factors.
Balanced Neural ODEs combine VAEs and Neural ODEs for efficient time series modeling.
problem Efficiently modeling systems with time-varying inputs and varying complexity.
method Combines VAEs for dimensionality reduction and Neural ODEs for dynamics, using variational parameters to adaptively learn.
result Balanced Neural ODEs (B-NODE) efficiently approximate Koopman operator without predefined dimensionality.
In this work we show that the systems of balance equations (balance systems) of continuum thermodynamics occupy a natural place in the variational bicomplex formalism. We apply the vertical homotopy decomposition to get a local splitting (in a convenient domain) of a general balance system as the sum of a Lagrangian pa…
New deep learning method improves financial stress testing accuracy.
problem Traditional stress testing methods are criticized for unrealistic assumptions and estimation errors.
method Proposes a novel Deep Learning approach for Dynamic Balance Sheet Stress Testing.
result Empirical results show significant improvement in accuracy over traditional methods.
Urban transformations within large and growing metropolitan areas often generate critical dynamics affecting social interactions, transport connectivity and income flow distribution. We develop a statistical-mechanical model of urban transformations, exemplified for Greater Sydney, and derive a thermodynamic descriptio…
BLISS optimizes GNN training by adaptively sampling nodes.
problem High computational costs in training GNNs on large graphs.
method Uses Bandit Layer Importance Sampling to dynamically select nodes.
result Improves GNN performance with reduced computational cost.
Many complex systems exhibit extreme events far more often than expected for a normal distribution. This work examines how self-similar bursts of activity across several orders of magnitude can emerge from first principles in systems that adapt to information. Surprising connections are found between two apparently unr…
A method removes treatment-covariate dependence for counterfactual prediction without adversarial training.
problem Counterfactual prediction under assignment bias.
method Information-theoretic approach learning a stochastic representation Z to minimize mutual information with outcomes.
result The method performs favorably in likelihood, counterfactual error, and policy evaluation compared to adversarial baselines.
Researchers derive a new equation for valuing American options.
problem Valuation and hedging of American options on dividend-paying assets.
method Derive a stochastic balance equation for the value function and its gradient.
result The derived equation uniquely solves the valuation problem.
CBDA improves active learning for semantic segmentation, especially with imbalanced classes.
problem Class imbalance degrades performance in domain adaptive active learning.
method Class Balanced Dynamic Acquisition (CBDA) selects more balanced labels for active learning.
result CBDA increases minority class performance and outperforms baselines by 0.6-2.4 mIoU.
In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics. A stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is large. The sto…
Data balancing reduces variance in machine learning models.
problem Reduction of variance in machine learning models.
method Non-asymptotic statistical bound and eigenvalue decay of Markov operators.
result Data balancing across modalities and sources reduces variance.
This paper describes a method for learning low-dimensional approximations of nonlinear dynamical systems, based on neural-network approximations of the underlying Koopman operator. Extended Dynamic Mode Decomposition (EDMD) provides a useful data-driven approximation of the Koopman operator for analyzing dynamical syst…
IDS improves sparse linear bandits by balancing information and regret.
problem Sparse linear bandits in high-dimensional decision-making.
method Information-directed sampling (IDS) with Bayesian regret bounds and empirical Bayesian sparse posterior sampling.
result IDS nearly matches existing lower bounds and significantly reduces regret.