Continuous-time distributed mirror descent with integral feedback converges to global optimum.
problem Distributed optimization of a global strongly convex function with local convex components.
method Continuous-time distributed mirror descent with integral feedback.
result Asymptotic convergence to global optimum with constant step-size.
Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.
problem Control jump-diffusion processes with unknown coefficients in reinforcement learning.
method Lipschitz continuous optimal feedback controls, stability analysis of forward-backward SDEs, least-squares algorithm.
result Achieves O ( N ln N ) O(\sqrt{N\ln N}) O ( N ln N ) regret for linear-convex learning problems with jumps. New algorithm learns Gaussian policies from corrective human feedback, outperforming current methods.
problem Learning from corrective human feedback for complex systems.
method Gaussian Process Coach (GPC) that uses Gaussian Processes and policy uncertainty for optimal feedback selection and learning rate adaptation.
result Demonstrated superior performance in OpenAI Gym benchmarks compared to COACH.
Improved GRU model with weighted time-delay feedback for long-term dependencies.
problem Modeling long-term dependencies in sequential data.
method Introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism.
result τ-GRU outperforms state-of-the-art models on various tasks.
Paper improves parameter estimation of continuous distributions using preference feedback.
problem Improving parameter estimation of continuous distributions.
method Preference-based M-estimators and deterministic preferences.
result Preference-based estimators achieve an estimation error scaling of O(1/n), significantly faster than sample-only methods.
A method for training autonomous vehicles using continuous human feedback to avoid sub-optimal decisions.
problem Training autonomous vehicles with limited and potentially sub-optimal human demonstrations.
method Continuous scalar feedback for each action to learn from sub-optimal demonstrations and evaluative feedback.
result The proposed method outperforms supervised learning on positive examples alone and learns from sub-optimal demonstrations.
Proposes deep optimal feedback control for continuous-time systems with action constraints.
problem Learning optimal feedback control laws for robotic applications.
method Exploits Hamilton-Jacobi-Bellman equation and deep differential networks to learn optimal value function and feedback policy.
result Enables learning an optimal feedback control law that generates an optimal trajectory from any point in state-space without replanning.
New STDP rule for spiking neurons solves discrete action reinforcement learning tasks.
problem Applying standard STDP to discrete action reinforcement learning tasks.
method Feedback-modulated TD-STDP learning rule for spiking neuron networks.
result Feedback modulation improves credit assignment in reinforcement learning.
Develops hedging algorithm for online expert weight allocation with delayed feedback.
problem Adaptive hedging strategies for online expert weight allocation with delayed feedback.
method General Hedging algorithm G \mathcal{G} G based on exponential reweighing of experts' losses. result Proves adversarial loss bounds for the General Hedging algorithm G \mathcal{G} G in the delayed feedback setting. Three online algorithms for submodular maximization with varying feedback types.
problem Maximizing submodular functions under different feedback models.
method Mono-Frank-Wolfe, Bandit-Frank-Wolfe, Responsive-Frank-Wolfe.
result Achieved ( 1 − 1 / e ) (1-1/e) ( 1 − 1/ e ) -regret bounds for each algorithm. New method uses feedback to improve deep reinforcement learning efficiency.
problem Vast amounts of data needed for reasonable performance in deep reinforcement learning.
method Binary corrective feedback combined with probabilistic conditional exploration.
result Achieves drastic improvements in sample efficiency and robustness.
This paper extends a Kyle model to include price-responsive traders, revealing new dynamics and equilibria.
problem Real-world market dynamics involve price-responsive traders, affecting market equilibrium and insider profits.
method Developed a continuous-time Kyle model with two types of price-responsive traders (momentum and contrarian), leading to a forward-backward Riccati system for equilibrium.
result The model shows that feedback effects can lead to multiple equilibria and amplify price informativeness.
Neural ODEs control graph dynamics with low energy feedback.
problem Controlling complex dynamical systems on graphs.
method Neural Ordinary Differential Equation Control (NODEC) framework.
result NODEC learns low-energy control signals for graph dynamical systems.
We analyze a controlled price formation experiment in the laboratory that shows evidence for bubbles. We calibrate two models that demonstrate with high statistical significance that these laboratory bubbles have a tendency to grow faster than exponential due to positive feedback. We show that the positive feedback ope…
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper…
A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods for alleviating catastrophic forgetting are currently being proposed, but diffe…
New study shows feedback doesn't improve MAB performance over erasure channels.
problem Distributed multi-armed bandit problem with arm erasure channels.
method Analyzed MAB with feedback and erasure channels, proving no improvement in regret.
result Regret lower bound of Ω(√KT + K / (1 - ε)) matches no-feedback upper bounds.
This paper tackles delayed feedback in continuous training for CTR prediction, improving model performance by 3%.
problem Delayed feedback in CTR prediction leads to inferior performance and user experience.
method Comparing 5 loss functions and models in offline and online settings.
result Proposed methods outperform previous state-of-the-art by 3% relative cross entropy (RCE).
New algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.
problem Delayed feedback in Lipschitz bandits.
method Design of algorithms for bounded and unbounded stochastic delays.
result Sublinear regret guarantees for both bounded and unbounded delays.
RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST) for PO with mediator feedback.
problem Policy Optimization in continuous control tasks.
method RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST) for regret minimization in PO.
result Achieving constant regret under certain circumstances in PO with mediator feedback.
New framework tackles submodular welfare with multi-agent combinatorial bandits.
problem Maximizing total welfare among agents with shared constraints and submodular utilities under bandit feedback.
method Proposes an explore-then-commit strategy with randomized assignments for multi-agent combinatorial bandits.
result Achieves i l d e O ( T 2 / 3 ) ilde{\mathcal{O}}(T^{2/3}) i l d e O ( T 2/3 ) regret, first for partition-based submodular welfare problem under bandit feedback. We propose a method for learning cyclic causal models from a combination of observational and interventional equilibrium data. Novel aspects of the proposed method are its ability to work with continuous data (without assuming linearity) and to deal with feedback loops. Within the context of biochemical reactions, we a…
FA algorithm provides convergence guarantees for deep linear networks.
problem Training efficiency and convergence of deep neural networks.
method Theoretical analysis of Feedback Alignment (FA) algorithm for deep linear networks.
result Certain initializations lead to implicit anti-regularization, affecting learning effectiveness.
According to the volatility feedback effect, an unexpected increase in squared volatility leads to an immediate decline in the price-dividend ratio. In this paper, we consider the properties of stock price dynamics and option valuations under the volatility feedback effect by modeling the joint dynamics of stock price,…
Study incentivizes exploration in non-stationary MAB with compensation.
problem Incentivized exploration for non-stationary stochastic bandits with biased feedback.
method Proposed algorithms for abruptly-changing and continuously-changing non-stationary environments.
result Achieves sublinear regret and compensation over time.
Maximizing trading volume in online learning framework between traders.
problem Maximizing the total number of trades between traders with unknown valuations.
method Developed algorithms for brokers to maximize trading volume under different feedback scenarios.
result Achieved logarithmic and poly-logarithmic regret rates for different feedback models.
Infrastructure monitors AI/ML radiology models across multiple sites.
problem Monitoring and improving AI/ML radiology models across multiple sites.
method Interactive radiology reporting, centralized cloud system, post-marketing surveillance.
result Efficient monitoring and iterative development of AI/ML models without radiologist burden.
The paper tackles learning from imperfect human feedback, especially in dueling bandit problems.
problem Learning from human feedback that can be irrational or imperfect.
method Developed a Robustified Stochastic Mirror Descent for Imperfect Dueling (RoSMID) algorithm.
result Achieved nearly optimal regret for dueling bandit problems under imperfect human feedback.
Study apple tasting feedback in online binary classification, providing new insights into minimax expected mistakes.
problem Online binary classification with partial feedback (apple tasting).
method Combinatorial analysis, Littlestone dimension, Effective width.
result Established a trichotomy of minimax expected mistakes in the realizable setting.
RTM extends TM for continuous output problems using conjunctive clauses.
problem Continuous output problems in machine learning.
method Modified inner inference mechanism to produce a single continuous output.
result RTM achieves better regression accuracy with fewer clauses.
Language models learn automotive complaints, improving defect detection.
problem Detecting technical quality issues in customer feedback.
method Continual pre-training on ODI Complaints data set.
result Models achieve high precision in identifying technical terms.
Extended flatness approach for discrete-time systems considers forward and backward shifts.
problem Defining flatness for discrete-time systems with forward-shifts.
method Introducing backward-shifts to extend flatness definition.
result Extended flat systems maintain key properties like reachability and controllability.
The paper tackles exact linearization and control of flat discrete-time systems.
problem Exact linearization and control of flat nonlinear discrete-time systems.
method Investigates conditions for choosing new inputs and feedbacks that may depend on forward-shifts of the new input.
result Easily verifiable conditions for choosing a feasible input and a new input that minimizes forward-shifts of the flat output.
Mutation improves FTRL convergence in zero-sum games.
problem Lack of last-iterate convergence in FTRL variants.
method Introduced mutation to perturb action probabilities in FTRL.
result M-FTRL converges to Nash equilibria under full-information feedback.
Learning weights in a spiking neural network with hidden neurons, using local, stable and online rules, to control non-linear body dynamics is an open problem. Here, we employ a supervised scheme, Feedback-based Online Local Learning Of Weights (FOLLOW), to train a network of heterogeneous spiking neurons with hidden l…
Generative model solves financial market equilibria with stable reinforcement learning.
problem Financial market equilibria under realistic frictions and multiple agents.
method Generative adversarial reinforcement learning with decoupling feedback.
result Algorithm learns and predicts asset returns and volatilities.
This work refines imitation learning to approximate optimal state-feedback policies for a quadcopter model.
problem Designing optimal control policies for complex systems like quadcopters.
method Supervised imitation learning using deep neural networks trained on optimal trajectories.
result Deep neural networks can approximate optimal state-feedback policies with high accuracy, even with two layers.
This research introduces an autonomous robot navigation method using reinforcement learning.
problem Improving robot navigation in complex environments.
method Deep Q Network (DQN) and Proximal Policy Optimization (PPO) models for path planning and decision-making.
result The models enhance robot navigation ability and adaptive learning in unknown environments.
Proposes estimators for complex dose-response curves using kernel methods.
problem Estimating complex dose-response curves with continuous treatments, mediators, and covariates.
method Kernel ridge regression with sequential kernel embedding technique.
result Simple estimators for mediated and time-varying dose response curves with nonasymptotic uniform rates.
We extend a model of positive feedback and contagion in large mean-field systems, by introducing a common source of noise driven by Brownian motion. Although the driving dynamics are continuous, the positive feedback effect can lead to `blow-up' phenomena whereby solutions develop jump-discontinuities. Our main results…
Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns. Such reward signals represent the immediate feedback of a partic…
Study learns optimal bidding strategy in auctions with dynamic values and aggregated feedback.
problem Optimizing bidding in auctions with time-dependent values and limited feedback.
method Combines plug-in estimators with differential-equation characterization of optimal policy.
result Achieves near optimal regret bounds for learning optimal policy.
Improved error feedback method reduces communication complexity in distributed training.
problem Improving convergence in distributed training methods with compression techniques.
method Introduced and improved a modern form of error feedback (EF21) by reducing its theoretical communication complexity.
result Communication complexity depends on the arithmetic mean of smoothness parameters, leading to significant improvements.
A neuro-inspired architecture learns without supervision using clustering and predictive coding.
problem Achieving continual learning without supervision.
method Neuro-inspired architecture based on online clustering and hierarchical predictive coding.
result The architecture achieves continual learning without supervision.
RL approach to continuous-time MV portfolio selection with optimal policy being Gaussian.
problem Achieving optimal tradeoff between exploration and exploitation in continuous-time MV portfolio selection.
method Entropy-regularized, relaxed stochastic control problem; policy improvement theorem; RL algorithm.
result RL algorithm outperforms adaptive control and deep neural networks methods.
A PID-based feedback-control system improves multiple KPIs in RTB display advertising.
problem Challenges in simultaneously improving multiple KPIs in RTB campaigns.
method Sequential Control using PID-based feedback and importance metrics.
result Effective in simultaneously controlling multiple KPIs in both simulations and live traffic.
In a wide variety of applications, humans interact with a complex environment by means of asynchronous stochastic discrete events in continuous time. Can we design online interventions that will help humans achieve certain goals in such asynchronous setting? In this paper, we address the above problem from the perspect…
Proposes DRRO to mitigate over-optimization in RLHF from human feedback.
problem Over-optimization due to reward misspecification in RLHF.
method Wasserstein distributionally robust regret optimization (DRRO).
result DRRO mitigates over-optimization more effectively than existing baselines.