New measure of interference helps understand and mitigate learning issues in reinforcement learning.
problem Understanding and mitigating interference in reinforcement learning.
method Defined a new measure of interference, evaluated it, and identified key factors contributing to interference.
result Target network frequency and updates on the last layer are significant factors in interference.
New method removes interference bias in causal models.
problem Interference bias impedes causal effect identification in real-world settings.
method Novel definition of causal models with local interference, semi-parametric assumptions.
result True Average Causal Effect can be identified in certain semi-parametric models with local interference.
Estimates causal effects in networks with varying interference.
problem Estimating causal effects in settings with network interference.
method Proposes neighborhood adaptive estimators for average direct treatment effect on the treated.
result Establishes rates of convergence and distributional results for proposed estimators.
TD learning reduces interference, leading to better generalization.
problem Understanding and reducing interference in TD learning for better generalization.
method Analyzing the inner product of gradients as interference, comparing TD and supervised learning, and examining the dynamics of interference and bootstrapping.
result TD learning leads to low-interference, under-generalizing parameters, while supervised learning does the opposite.
Deep learning (DL) based autoencoder has shown great potential to significantly enhance the physical layer performance. In this paper, we present a DL based autoencoder for interference channel. Based on a characterization of a k-user Gaussian interference channel, where the interferences are classified as different le…
The paper addresses Qini curve estimation under clustered network interference.
problem Qini curves can be biased when interference is ignored in clustered network settings.
method Proposes three estimation strategies for clustered network interference.
result Identifies the most appropriate approach based on bias-variance trade-offs.
Paper predicts interference for better LA in URLLC.
problem Improving LA for URLLC with strict latency and reliability.
method Exploits time correlation of interference for prediction.
result Predicted interference improves LA for URLLC.
DN estimator mitigates network interference in experiments.
problem Network interference biases naive experiment designs.
method Differences-in-Neighbors (DN) estimator designed to mitigate interference.
result DN achieves bias second order in interference effect, with exponentially smaller variance.
Study efficient inference for network quantile causal effects with partial interference.
problem Estimating network causal effects on outcome quantiles with partial interference.
method Developed a nonparametric efficiency theory and a nonparametrically efficient estimator using a three-way cross-fitting procedure.
result Proposed estimator is consistent, asymptotically normal, and allows flexible estimation of nuisance functions.
Spatial Deconfounder tackles interference and confounding in spatial data.
problem Interference and unmeasured spatial factors confound causal inference in spatial domains.
method Two-stage method using CVAE with spatial prior to reconstruct confounder, then estimate causal effects.
result Nonparametric identification of direct and spillover effects under weak assumptions.
Estimating individual treatment effects from data of randomized experiments is a critical task in causal inference. The Stable Unit Treatment Value Assumption (SUTVA) is usually made in causal inference. However, interference can introduce bias when the assigned treatment on one unit affects the potential outcomes of t…
Algorithm learns interference network and optimizes treatment allocation for unknown network effects.
problem Adaptive experimentation under unknown network interference.
method Thompson sampling algorithm with Gibbs sampler for joint learning of interference network and treatment allocation.
result Proves a Bayesian regret bound and achieves sublinear regret in real-world applications.
Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interference within an environment inhibits learning. We test this hypothesis through a large-scale empirical study in the Arcade Learning Environment (ALE) and, indeed, find supporting …
Bayesian method estimates causal effects with proxy networks.
problem Estimating causal effects with only proxy measurements of a latent interference network.
method Structural causal model with Block Gibbs sampler and Locally Informed Proposals.
result Accurately estimates causal effects even with noisy proxy networks.
Machine learning method characterizes network interference in A/B tests.
problem Compromised A/B test reliability due to network interference.
method Causal network motifs and machine learning models.
result Outperforms conventional methods in characterizing network interference.
FRONT optimizes decisions with interference, reducing regret over time.
problem Short-sighted policies in online decision-making due to ignoring interference.
method FRONT considers long-term impacts of decisions, using exploratory and exploitative strategies.
result FRONT achieves sublinear regret in both immediate and consequential impacts.
The paper tackles adaptive targeting in networks with interference effects.
problem Adaptive targeting under network interference in a bandit setting.
method Linear model in a sparse regime, analyzing different levels of knowledge of the interference structure.
result Unified view of how knowledge of the interference structure affects online learning efficiency.
This article proposes and evaluates a technique to predict the level of interference in wireless networks. We design a recursive predictor that estimates future interference values by filtering measured interference at a given location. The predictor's parameterization is done offline by translating the autocorrelation…
New algorithm optimizes interventions under network interference, scaling to large networks.
problem Optimal policy learning under network interference where one individual's treatment affects others.
method Developed a scalable Thompson sampling algorithm for dynamic networks.
result Proved a Bayesian regret bound that is sublinear in network size and rounds.
A new method reduces task interference in model merging.
problem Model merging overlooks structural information and is susceptible to task interference.
method Task Singular Vectors (TSV) and TSV-Compress for compression and interference reduction.
result TSV-Merge significantly outperforms existing methods.
Interference effects of tall buildings have attracted numerous studies due to the boom of clusters of tall buildings in megacities. To fully understand the interference effects of buildings, it often requires a substantial amount of wind tunnel tests. Limited wind tunnel tests that only cover part of interference scena…
New algorithm minimizes regret in multi-armed bandits with network interference.
problem Minimizing regret in online experiments with network interference.
method Sparse network interference model, discrete Fourier analysis, linear regression-based algorithms.
result Provable low regret algorithms for sparse interference networks.
New method improves causal inference by estimating complex treatment effects with active learning.
problem Traditional causal inference frameworks ignore interference and assume independent treatment effects.
method Active Learning in Causal Inference with Interference (ACI) using Gaussian process and genetic algorithms.
result ACI achieves accurate effects estimation with reduced data requirements in complex interference scenarios.
New framework for estimating treatment effects in experiments with network interference.
problem Network interference biases traditional treatment effect estimations in randomized experiments.
method Causal message-passing framework based on high-dimensional approximate message passing.
result Practical algorithm to estimate total treatment effect in multi-period experiments.
New estimator reduces bias in interference studies on content marketplaces.
problem Interference bias in experiments on content marketplaces like Douyin.
method Developed a Monte-Carlo estimator based on DQ techniques.
result Achieved bias second-order in treatment effect with low variance.
New method HNCI for evaluating treatment effects in network interference.
problem Evaluating the effectiveness of treatments or policies under network interference.
method High-dimensional network causal inference (HNCI) using linear regression with latent homogeneity.
result Valid confidence intervals and sets for average direct treatment effect and neighborhood size.
New model tackles interference in online experiments.
problem Understanding cumulative performance in interference experiments.
method Introduces Multi-Armed Bandits with Interference (MABI) model.
result Cluster randomization policy achieves optimal expected regret and high probability bound.
An intervention may have an effect on units other than those to which it was administered. This phenomenon is called interference and it usually goes unmodeled. In this paper, we propose to combine Lauritzen-Wermuth-Frydenberg and Andersson-Madigan-Perlman chain graphs to create a new class of causal models that can re…
Estimates treatment effects in bipartite systems with partial eligibility and interference.
problem Randomized experiments in bipartite systems with partial treatment eligibility and interference.
method Formalizes eligibility-constrained bipartite experiments, defines PTTE and STTE, identifies conditions, develops ensemble estimators, introduces projection.
result Proposed estimators recover PTTE and STTE with low bias and variance, corrects interference bias in field experiments.
New method estimates treatment effects in complex interference settings.
problem Challenges in estimating treatment effects due to unknown interference.
method Higher-order causal message passing for non-linear feature learning.
result Effective estimation of treatment effect dynamics in complex interference.
Paper uses SC to estimate hidden interference for WSRM.
problem Maximizing sum-rate with hidden interfering sources.
method Synthetic control (SC) for estimating counterfactual interference in WMMSE.
result SC-WMMSE outperforms original WMMSE in convergence and objective.
The paper proposes an evolution-based approach to estimate causal effects in interference networks without fully observing the network structure.
problem Estimating causal effects in complex systems with unobserved interaction pathways.
method An evolution-based approach that characterizes how outcomes change across observation rounds in response to interventions, using an exposure-mapping perspective.
result The approach identifies minimal structural conditions under which evolution mappings exist, enabling consistent learning about heterogeneous spillover effects.
U-Net trained to recover acoustic interference striations from distorted data.
problem Recovering acoustic interference striations from distorted signals.
method Training a U-Net using a random mode-coupling matrix model to generate training data.
result U-Net successfully recovers AISs under various conditions.
New framework minimizes interference and selection bias in network A/B testing.
problem Interference and selection bias in network A/B testing.
method Proposes a principled framework that jointly minimizes interference and selection bias using edge spillover probability and cluster matching.
result Significantly lower error in causal effect estimation compared to existing solutions.
A new causal deepset framework improves off-policy evaluation under complex interference.
problem Handling spatio-temporal interference in off-policy evaluation.
method Permutation invariance assumption and novel algorithms incorporating it.
result Significantly more precise estimations than existing methods.
Researchers develop a method to measure treatment effects in settings with shared states.
problem Measuring treatment effects in settings with shared states like prices, recommendations, or social signals.
method Double machine learning (DML) theorem with conditions for efficient inference under shared-state interference.
result Efficient estimation of average direct effect (ADE) and global average treatment effect (GATE) in various models.
New framework validates counterfactual estimations in network interference settings.
problem Challenges in causal effect estimation and validation in network interference settings.
method Introduces a distribution-preserving network bootstrap and counterfactual cross-validation procedure.
result Validates counterfactual estimations in diverse network interference settings.
SON-GOKU uses graph coloring to improve multi-task learning by partitioning tasks into compatible groups.
problem Gradient interference between conflicting multi-task learning objectives slows convergence and model performance.
method SON-GOKU computes gradient interference, constructs an interference graph, and applies greedy graph-coloring to partition tasks.
result SON-GOKU consistently outperforms baselines and state-of-the-art multi-task optimizers on six datasets.
Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms. We study the learning dynamics of reinforcement learning (RL), specifically a characteristic coupling between learning and data generation that arises because RL agents control their future data distribution. I…
New estimator reduces bias-variance tradeoff in Markovian interference experiments.
problem Estimating impact of interventions in systems with limited resources.
method Differences-In-Q (DQ) estimator for on-policy policy evaluation.
result DQ estimator has exponentially smaller variance than off-policy methods.
A new method for reinforcement learning scales errors without tuning.
problem Error scaling varies across reinforcement learning tasks and stages.
method A simple scaling mechanism for temporal-difference learning.
result The method effectively mitigates interference between learning tasks.
The paper tackles robust design selection for online experiments under uncertain interference mechanisms.
problem Designing experiments in ads, recommendations, and member-experience systems when interference mechanisms are unknown.
method Formulates the problem as robust design selection over uncertain exposure mechanisms. Compares designs by worst-case planning risk over an ambiguity set combining various factors.
result Develops a geometry-aware guarantee and robust selector theorem with excess-risk control, exact recovery under separation, and certified shortlists when the risk surface is flat.
A robust method for decomposing spectral peaks robust to distortion and interference.
problem Decomposing spectral peaks in the presence of distortion and interference.
method Optimizing a nonparametric approach using pseudo-symmetric functions with nonincreasing behavior.
result Decomposed spectral peaks show pseudo-orthogonal behavior and power preserving equality.
The paper optimizes spatial experimental designs to improve causal effect estimation.
problem Optimizing spatial experimental designs to enhance causal effect estimation accuracy.
method Proposes a surrogate function for MSE and uses graph cut algorithms to learn optimal designs.
result The method accommodates spatial interference and covariance, is computationally efficient, and validated by theoretical and numerical experiments.
A new framework for causal inference in networked settings.
problem Causal inference under network interference.
method Characterize agent network configuration and use it to estimate treatment effects.
result Finite-sample bounds and asymptotically valid tests for policy irrelevance.
Bayesian active learning tackles nuisance parameters, leading to bias and dilemmas.
problem Bayesian active learning with nuisance parameters leads to bias and dilemmas.
method Characterizes and mitigates negative interference by accurately estimating nuisance parameters.
result The extent of negative interference can be extremely large, and accurate estimation of nuisance parameters is critical.
Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off …
Gradient-based meta-learning has proven to be highly effective at learning model initializations, representations, and update rules that allow fast adaptation from a few samples. The core idea behind these approaches is to use fast adaptation and generalization -- two second-order metrics -- as training signals on a me…