VFDS selects dynamic features for efficient HAR tasks, optimizing performance-cost trade-offs.
problem Optimizing feature selection for varying costs and dynamic contexts in machine learning tasks.
method Bayesian learning framework with variational dynamic selection policy.
result VFDS selects different features under changing contexts, saving sensory costs while maintaining HAR accuracy.
Flexible deep learning models for dynamic accuracy and speed trade-offs.
problem Dynamic accuracy and speed trade-offs in real-world applications.
method Training deep neural networks with a new method allowing flexible numerical precision during inference.
result Achieved comparable accuracy to dedicated models trained at the same precision with dynamic precision settings.
Recursive least-squares algorithms often use forgetting factors as a heuristic to adapt to non-stationary data streams. The first contribution of this paper rigorously characterizes the effect of forgetting factors for a class of online Newton algorithms. For exp-concave and strongly convex objectives, the algorithms a…
Improved neural network depth-width trade-offs via dynamical systems.
problem Expressivity of neural networks in terms of depth and width.
method Connection with dynamical systems, focusing on periodic points and Lipschitz constants.
result Sharper width lower bounds for neural networks, yielding exponential depth-width separations.
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.
Unified analysis of DLNs using DMFT reveals dynamics of loss convergence and generalization trade-offs.
problem Understanding the overall dynamics of diagonal linear networks (DLNs) in neural network training.
method Dynamical Mean-Field Theory (DMFT) applied to DLNs.
result Derives low-dimensional effective process capturing high-dimensional gradient flow dynamics.
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. Paper tackles bias-variance trade-off in missing data, proposing a dynamic framework.
problem Missing data in practical applications deteriorates model performance.
method Develops a fine-grained dynamic learning framework to jointly optimize bias and variance.
result Theoretical and empirical validation of joint bias-variance optimization.
Algorithm achieves optimal pricing with minimal exploration for dynamic markets.
problem Optimal pricing in dynamic markets with contextual information.
method Localized exploration-then-commit (LetC) algorithm with pure exploration, refinement, and exploitation stages.
result Achieves minimax optimal, dimension-free regret bound.
This study develops a multi-factor framework where not only market risk is considered but also potential changes in the investment opportunity set. Although previous studies find no clear evidence about a positive and significant relation between return and risk, favourable evidence can be obtained if a non-linear rela…
We address the problem of estimating the inputs of a dynamical system from measurements of the system's outputs. To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the overall estimation error. This optimal trade-off is done efficiently and adaptively…
Bayesian optimization offers the possibility of optimizing black-box operations not accessible through traditional techniques. The success of Bayesian optimization methods such as Expected Improvement (EI) are significantly affected by the degree of trade-off between exploration and exploitation. Too much exploration c…
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the D2NN itself. By pruning unnecessary computation depending on input, D2NNs provide a…
New connection between DNNs and Sharkovsky's Theorem for depth-width trade-offs.
problem Understanding why some functions are hard to represent by shallow ReLU networks.
method Connection to Sharkovsky's Theorem and analysis of dynamical systems.
result Lower bounds for width needed to represent periodic functions as a function of depth.
Study aims to optimize financial investments by balancing risk and reward efficiently.
problem Balancing risk and reward in dynamic financial investments.
method Proposes a reinforcement learning method to maximize expected quadratic utility, focusing on first and second moments of rewards.
result The proposed method yields MV-efficient policies that maximize expected reward without increasing variance.
Market makers face a trade-off between fill probability and post-fill returns, requiring contrarian strategies.
problem Navigating the trade-off between fill probability and post-fill returns in market making.
method Analysis of live trading data from Binance Bitcoin perpetual.
result A negative correlation between maker fill likelihood and post-fill returns, necessitating contrarian strategies.
We propose the use of incomplete dot products (IDP) to dynamically adjust the number of input channels used in each layer of a convolutional neural network during feedforward inference. IDP adds monotonically non-increasing coefficients, referred to as a "profile", to the channels during training. The profile orders th…
RACER optimizes LLM-as-judge accuracy with dynamic reasoning selection.
problem Balancing reasoning accuracy with computational cost in LLM-as-judge settings.
method Formulates routing as a constrained distributionally robust optimization problem, accounting for distribution shift via KL-divergence uncertainty set.
result RACER achieves superior accuracy-cost trade-offs under distribution shift.
Study risk-sensitive reinforcement learning with Lipschitz dynamic risk measures, establishing regret bounds.
problem Risk-sensitive reinforcement learning in Markov decision processes.
method Two model-based algorithms for Lipschitz dynamic risk measures, focusing on regret bounds.
result Upper bounds demonstrate optimal dependencies on actions and episodes, reflecting risk sensitivity vs. sample complexity trade-off.
Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbit…
Paper combines RL with classifiers to improve financial trading strategies.
problem Enhancing risk-return trade-offs in trading strategies.
method Combining Reinforcement Learning (RL) models with traditional classifiers like SVM, Decision Trees, and Logistic Regression.
result Ensemble methods often outperform base models in risk-adjusted returns.
Free lunch from noise reveals linear spectral features for RL.
problem Trade-off between expressiveness and tractability in RL.
method Noise assumption and Spectral Dynamics Embedding (SPEDE).
result SPEDE breaks the trade-off and completes optimistic exploration.
AI-driven tax policies improve economic equality and productivity.
problem Lack of appropriate economic data and limited opportunity to experiment.
method Two-level deep reinforcement learning approach to learn dynamic tax policies from observational data.
result AI-driven tax policies improve the trade-off between equality and productivity by 16%.
The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are possible if all beliefs are Gaussian processes. A first order approximation of learn…
In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities. Since natural systems have smooth dynamics, an opportunity is lost if an unsupervised objective function remains static during the training process. The absence of concre…
VAE struggles with distribution class sharpness, which can be learned dynamically.
problem VAE struggles with distribution class sharpness, leading to blurry reconstructions.
method Established that VAE fails if distribution class sharpness does not match data scale. Suggested learning distribution sharpness dynamically.
result Dynamic adjustment of distribution sharpness improves VAE performance, escaping local optima.
Autonomous lane changing is a critical feature for advanced autonomous driving systems, that involves several challenges such as uncertainty in other driver's behaviors and the trade-off between safety and agility. In this work, we develop a novel simulation environment that emulates these challenges and train a deep r…
The question is: What does happen to the real-world networks which cause them not to grow permanently? The idea here is that real-world networks have to pay the cost of growth. We investigate the growth and trade-off between value and cost in the networks with cost and preferential attachment together. Since the prefer…
Dynamic model considers private asset markets' complexities.
problem Understanding and optimizing private asset allocation.
method State-of-the-art dynamic model with machine learning.
result Optimal investment policies quantified over fund life.
Study maps interdependence of SDGs, finds complex, dynamic linkages.
problem Identify which SDGs promote progress and how quickly.
method Used a balanced panel of 114 countries from 2000 to 2024, applying two estimators to recover directed interaction network and measure dynamic linkages.
result 84 goal linkages survive false-discovery control, showing both synergies and trade-offs, with no single goal acting as a universal accelerator.
Many real-world systems studied are governed by complex, nonlinear dynamics. By modeling these dynamics, we can gain insight into how these systems work, make predictions about how they will behave, and develop strategies for controlling them. While there are many methods for modeling nonlinear dynamical systems, exist…
VRER selectively reuses past observations to reduce variance in policy optimization.
problem Lack of effective experience replay for accelerating policy optimization in complex systems.
method Variance Reduction Experience Replay (VRER) framework that selectively reuses informative samples.
result VRER reduces gradient variance and improves policy learning over state-of-the-art algorithms.
New method selects data points for better model performance.
problem Balancing input coverage and model utility in selective prediction.
method Study training dynamics to reject inputs with unstable predictions.
result State-of-the-art selective prediction performance achieved without model modifications.
Adaptive batch sizes improve active learning efficiency and flexibility.
problem Fixed batch sizes in active learning are inefficient due to dynamic cost-speed trade-offs.
method Probabilistic Numerics framework that adaptively changes batch sizes based on integration error and precision objectives.
result Significant enhancement in learning efficiency and flexibility across various applications.
GeLoRA optimizes LoRA fine-tuning by dynamically adjusting ranks based on intrinsic dimensionality.
problem Efficient fine-tuning of large language models with limited computational resources.
method GeLoRA computes intrinsic dimensionality to adaptively select LoRA ranks, balancing expressivity and efficiency.
result GeLoRA consistently outperforms recent baselines within the same parameter budget on multiple tasks.
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization appr…
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to sequentially acquire a subset of the information while balancing accuracy and fairness …
Reduced modeling of a computationally demanding dynamical system aims at approximating its trajectories, while optimizing the trade-off between accuracy and computational complexity. In this work, we propose to achieve such an approximation by first embedding the trajectories in a reproducing kernel Hilbert space (RKHS…
Dynamic acquisition of features improves predictions with limited data.
problem Limited or uncertain data requires additional relevant information for accurate assessments.
method Proposes models that dynamically acquire new features using conditional mutual information and arbitrary conditional flow.
result Demonstrates superior performance over baselines in multiple settings.
Markov chains and diffusion processes are indispensable tools in machine learning and statistics that are used for inference, sampling, and modeling. With the growth of large-scale datasets, the computational cost associated with simulating these stochastic processes can be considerable, and many algorithms have been p…
DYffusion improves diffusion models for spatiotemporal forecasting.
problem Challenges in generating stable and accurate forecasts for dynamic data.
method Leverages temporal dynamics in data, directly coupling it with diffusion steps.
result Improves computational efficiency and performs competitively on complex dynamics.
A new algorithm avoids worst-case outcomes in risky contexts.
problem Risk-averse behavior in contextual bandits is challenging.
method Developed a first risk-averse contextual bandit algorithm with online regret guarantees.
result First algorithm with an online regret guarantee for risk-averse contextual bandits.
In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in th…
The paper addresses dynamic capital structure models with defaultable debt, proving existence and uniqueness.
problem Dynamic capital structure models with an investor break-even condition may not generate a contraction mapping.
method Provided an example and used a dual problem and change of measure to prove existence and uniqueness.
result A unique Markov-perfect equilibrium exists where firm decisions reflect state-dependent targets.
Langevin Dynamics speeds up mixing time with manifold hypothesis and multi-scale approach.
problem Langevin Dynamics struggles in high dimensions and nonconvex landscapes.
method Utilizes manifold hypothesis to reduce mixing time and employs multi-scale approach to improve image generation quality.
result Mixing time depends on intrinsic dimension rather than ambient dimension, significantly reducing computational complexity.
Dynamic submodular maximization with consistency constraints.
problem Maximizing submodular functions in a streaming environment with limited changes.
method Algorithms with trade-offs between consistency and approximation quality.
result Effective algorithms for real-world applications.
This paper speeds up simulations of hypersonic reentry by combining traditional and neural methods.
problem Accurately simulating hypersonic reentry with chemical reactions is computationally expensive.
method A hybrid simulation code combining a traditional fluid dynamics solver with a neural network approximating chemical reactions.
result Achieved significant acceleration factors (imes10 to imes18.6) while maintaining accuracy. LoRA fine-tuning causes forgetting, studied via particle system dynamics.
problem Catastrophic forgetting in LoRA fine-tuning.
method Mean-field self-attention model, partial differential equations, dynamical systems.
result Characterization of phase transitions in forgetting behavior.