The paper simplifies influence computations for large-scale machine learning models.
problem Improving training efficiency and accuracy in large-scale models.
method Study influence functions, define memorization, simplify computations.
result Influence functions can be practical for large-scale models, indicating memorization.
FlexEncoder analyzes DAE parameters' impact on recommender systems.
problem Varying parameter settings lead to different performance in DAE-based recommender systems.
method Built FlexEncoder with configurable parameters to analyze parameter influences.
result DAE parameters significantly affect prediction accuracy across datasets.
A new framework for structured bandits using influence diagrams and variational Thompson sampling.
problem Complex statistical dependencies in structured bandit problems.
method Influence diagram framework, variational Thompson sampling, tracking structured posterior distribution.
result Empirically evaluated algorithms perform as well as or better than existing baselines.
The rise of Online Social Networks (OSNs) has caused an insurmountable amount of interest from advertisers and researchers seeking to monopolize on its features. Researchers aim to develop strategies for determining how information is propagated among users within an OSN that is captured by diffusion or influence model…
Paper presents a new way to estimate model changes without full model evaluation.
problem Efficiently estimating changes in model parameters and outputs due to data point removal.
method Dual representation of influence functions for linearizable models, reducing computational complexity.
result The dual representation can be an efficient alternative to original influence functions, especially for large models.
The paper establishes a central limit theorem for estimating the influence parameter in a partially observed Hawkes process system.
problem Estimating the influence parameter in a partially observed Hawkes process system.
method Central limit theorem applied to an estimator of the influence parameter in a partially observed system of Hawkes processes.
result Establishes a central limit theorem for the estimator of the influence parameter under the subcritical condition.
Proposes second-order influence functions for identifying influential groups in test-time predictions.
problem Identifying influential groups in test-time predictions for black-box models.
method Second-order approximations of the effect of removing a group of training samples on model predictions.
result Improves the correlation between computed influence values and ground truth values for linear models.
Efficient estimators for smooth Hilbert-valued parameters with theoretical guarantees.
problem Estimating smooth Hilbert-valued parameters with theoretical guarantees.
method Pathwise differentiable Hilbert-valued parameters, efficient influence functions, regularized one-step estimators.
result Theoretical guarantees for efficient estimators even when nuisance functions are arbitrary.
Influence functions help study large language model generalization, revealing surprising decay patterns.
problem Understanding and mitigating risks in large language models (LLMs).
method Eigenvalue-corrected Kronecker-Factored Approximation (EK-FAC) to scale influence functions to LLMs.
result Influences decay to near-zero when key phrases order is flipped, revealing a surprising limitation.
Develops new methods to evaluate data influence in SAM for improved model training.
problem Challenges in mislabeled noisy data and privacy concerns in SAM.
method Two innovative data valuation methods based on influence functions (IF) for SAM.
result Demonstrates effectiveness in identifying mislabeled data and enhancing interpretability.
Gradient rollback explains neural models by identifying influential training examples.
problem Explain predictions of neural black-box models, especially in applications requiring user trust.
method Gradient rollback, a general approach for influence estimation applicable to neural models with limited parameter updates.
result Gradient rollback provides faithful explanations for neural models, including knowledge graph embedding methods.
We present a method for learning the parameters of a Bayesian network with prior knowledge about the signs of influences between variables. Our method accommodates not just the standard signs, but provides for context-specific signs as well. We show how the various signs translate into order constraints on the network …
Study analyzes Echo State Network parameters for Rossler attractor dynamics.
problem Understanding the influence of network type on Echo State Network performance.
method Experimental analysis of Echo State Network parameters using Rossler attractor.
result Exploration of how network type affects Echo State Network performance.
Study analyzes factors affecting profits in crypto liquidity provision.
problem Liquidity providers lack guidance for developing profitable strategies.
method Developed a measurement model based on impermanent loss to analyze key parameters.
result Uncovered influences of key parameters on LPs' profits.
Proposes a new sampling method for online learning with cumulative oversampling.
problem Budgeted Influence Maximization in online learning.
method Cumulative Oversampling (CO) method for online learning.
result CO-based algorithm achieves comparable regret to UCB-based algorithms and performs similarly to Thompson Sampling.
New IF method improves accuracy in deep neural networks with noisy data.
problem Inaccurate influence estimates in deep neural networks, especially with noisy data.
method Established a connection between influence estimation error, validation set risk, and sharpness, introducing a novel estimation form for flat validation minima.
result Our novel Influence Function approach provides more accurate influence estimates, validated across various tasks.
New algorithm for competing influence spread in unknown networks.
problem Maximizing influence spread in a social network with unknown probabilities.
method Combinatorial multi-armed bandit (CMAB) framework, Triggering Probability Modulated (TPM) condition, OCIM-TS, OCIM-OFU, OCIM-ETC.
result Sublinear Bayesian and frequentist regret for OCIM-TS and OCIM-OFU, respectively.
Proposes a new estimator for causal mediation with continuous treatments.
problem Estimation of direct and indirect effects with continuous treatments.
method Kernel smoothing approach with cross-fitting for non-parametric estimation.
result Multiply robust and asymptotically normal estimator for continuous treatments.
This study prioritizes temporal resolution over spatial in energy systems models due to higher influence.
problem The impact of spatial and temporal resolution on energy system models.
method Global sensitivity analysis to compare structural aspects, spatial, and temporal resolution.
result Temporal resolution has a higher influence on all results parameters compared to spatial resolution.
DataInf efficiently approximates data influence in large models, improving transparency and identifying mislabeled data.
problem Efficiently estimating data influence in large-scale models like LoRA-tuned LLMs and diffusion models.
method DataInf uses a closed-form expression to approximate influence scores efficiently.
result DataInf outperforms existing methods in computational and memory efficiency, accurately identifying influential data points.
Unified approach for estimating causal contrasts robust to model misspecification.
problem Estimating causal contrasts in non-parametric models with potential misspecification.
method A unifying approach using doubly-robust ℓ 1 \ell_1 ℓ 1 regularized estimation with cross-fitting and sample splitting. result Estimators are robust to misspecification of either nuisance function, ensuring consistent and normal asymptotic properties.
Study shows influence functions are poor for neural networks but useful for identifying influential examples.
problem Influence functions misalign with leave-one-out retraining in neural networks.
method Decomposed the discrepancy into five terms and studied their contributions across different architectures and datasets.
result Influence functions are a good approximation to the proximal Bregman response function (PBRF), useful for identifying influential examples.
The log returns of financial time series are usually modeled by means of the stationary GARCH(1,1) stochastic process or its generalizations which can not properly describe the nonstationary deterministic components of the original series. We analyze the influence of deterministic trends on the GARCH(1,1) parameters us…
Efficiently selects seed nodes to maximize content influence in unknown social networks.
problem Maximizing content spread in social networks with unknown network model.
method Formulated as an infinite-horizon discounted MDP, uses model-based reinforcement learning to select seed users adaptively.
result Established a regret bound of O ~ ( T ) \widetilde O(\sqrt{T}) O ( T ) for the algorithm. A new method debiases multiple target parameters without IFs.
problem Debiasing multiple target parameters in nonparametric models.
method Kernel Debiased Plug-in Estimation (KDPE) using TMLE and reproducing kernel Hilbert spaces.
result KDPE simultaneously debiases all pathwise differentiable target parameters.
Enhances influence functions for deep models without costly Hessian inversion.
problem Challenges in computing Hessian matrix inverse for deep models.
method Substitutes Hessian inverse with identity matrix and extends applications.
result TracIn method performs well in measuring model utility and fairness.
Unified theory for semiparametric data fusion with individual-level data.
problem Handling data fusion problems, especially in settings with diverse data sources and designs.
method Extending a comprehensive theory to handle conditional and marginal distribution alignments, providing universal results for influence functions and efficient influence functions.
result Paves the way for machine-learning debiased, semiparametric efficient estimation.
Q-Learning overestimation bias influenced by learning rate, discount factor, and reward signal.
problem Overestimation bias in Q-Learning algorithm.
method Investigated the influence of learning rate, discount factor, and reward signal on Q-Learning's overestimation bias. Tuned parameters and used an exponential moving average of reward signal.
result Q-Learning can achieve more accurate value estimates by tuning parameters and using an exponential moving average of reward signal.
Prediction-powered causal inference achieves smaller asymptotic variance than traditional methods.
problem Estimating causal and structural parameters in a semi-supervised setting.
method Combining efficient influence function with debiased machine learning and semi-supervised Riesz regression.
result Asymptotic variances of estimators match the derived efficiency bound.
Paper tackles hyper-gradient estimation in decentralized FL over time-varying networks.
problem Excessive communication costs and inability to use robust networks.
method Introduces an optimality condition and uses Push-Sum for averaging model parameters and gradients over time-varying directed networks.
result Derives a hyper-gradient estimator that operates over time-varying directed networks and converges to the true hyper-gradient.
The paper explores how symmetries and noise in SGD influence parameter dynamics.
problem Understanding the dynamics of parameter updates in SGD with symmetries.
method Proved the existence of noise equilibria and showed their role in balancing gradient noise.
result Gradient noise creates a systematic motion of parameters to a unique fixed point, called noise equilibria.
ULFS-KDPE estimates parameters efficiently without influence functions.
problem Estimating pathwise differentiable parameters in nonparametric models.
method Kernel debiased plug-in estimator based on universal least favorable submodel.
result Semiparametric efficiency achieved without influence function derivation.
Researchers study how teachers' advising relationships influence their perceptions of satisfaction and students, not policy influence.
problem Understanding the relationship between teachers' advising relationships and their perceptions of satisfaction and students.
method Proposed a novel joint model of network and item responses (JNIRM) with correlated latent variables.
result Teachers' advising relationships contribute more to satisfaction and students than to influence over educational policies.
Captures data influence changes during training.
problem Traditional influence functions fail for modern training methods.
method Formalized trajectory-specific LOO influence, using data value embedding.
result Data influence varies by training stage, early and late stages have greater impact.
New model for multivariate discrete event data with flexible interactions.
problem Modeling multivariate discrete event data with categorical interactions.
method Developed a new modeling approach with convex constraints, two estimation procedures (LS and ML).
result Proposed model can capture arbitrary shapes of historical event influence.
Social networks are getting closer to our real physical world. People share the exact location and time of their check-ins and are influenced by their friends. Modeling the spatio-temporal behavior of users in social networks is of great importance for predicting the future behavior of users, controlling the users' mov…
This paper presents the current state of a work in progress, whose objective is to better understand the effects of factors that significantly influence the performance of Latent Semantic Analysis (LSA). A difficult task, which consists in answering (French) biology Multiple Choice Questions, is used to test the semant…
Paper solves MFG for partially reversible investment, showing price influence and Nash equilibrium.
problem Solving MFG for partially reversible investment problems.
method Explicit solution for MFG, sensitivity analysis, comparison with single-agent control.
result Solution to MFG is an ε-Nash Equilibrium, ε=O(1/√N).
Simplifies efficient estimation via automatic differentiation and probabilistic programming.
problem Constructing efficient estimators for complex statistical models.
method Automatic differentiation applied to statistical functionals, avoiding the need to derive efficient influence functions.
result Users can generate efficient estimators with minimal code, simplifying the process for non-experts.
Model captures external influences through random parameters and regime switching.
problem Capturing external influences in asset dynamics with uncertainty and regime changes.
method Developed a stochastic model with random parameters and regime switching, mathematically consistent and interpretable.
result Demonstrated the model's versatility through local volatility models and characteristic functions.
Newfluence improves model interpretability in high-dimensional AI models.
problem Challenges in interpreting high-dimensional AI models.
method Introduced Newfluence, an alternative approximation to influence functions.
result Newfluence offers significantly improved accuracy in high-dimensional settings.
The paper develops coresets for panel data regression problems.
problem Efficiently summarize panel data regression problems.
method Introduced coreset construction for panel data regression problems using the Feldman-Langberg framework.
result Constructs coresets of size polynomial in 1/ ε \varepsilon ε and number of parameters, independent of panel data size. Investors' strategies in a market influenced by price impact are analyzed, showing aggressive behavior when impact exceeds a critical point.
problem Strategic interaction and Nash equilibria of investors in a financial market with price impact.
method Analysis of Nash equilibria for relative investors with CRRA and CARA utility functions in a Brownian motion-driven market, considering both linear and non-linear price impacts.
result Investors' aggressive behavior is observed when price impact exceeds a critical parameter.
Personalized recommendation systems (RS) are extensively used in many services. Many of these are based on learning algorithms where the RS uses the recommendation history and the user response to learn an optimal strategy. Further, these algorithms are based on the assumption that the user interests are rigid. Specifi…
In2Core selects a coreset for efficient LLM fine-tuning with reduced data.
problem Costly fine-tuning of large language models due to extensive parameters and data requirements.
method Analyzes model gradients to estimate training sample influence, optimizing for efficiency.
result Achieves similar performance with 50% of training data using In2Core.
GOIMDA selects inputs to maximize expected influence on a goal functional, reducing data acquisition needs.
problem Challenges in active data acquisition for learning and optimization tasks in deep neural networks.
method GOIMDA uses inverse curvature and goal gradient to select inputs maximizing expected influence on a specified goal functional.
result GOIMDA achieves target performance with fewer labeled samples or function evaluations compared to baselines.
Adapts randomization for single unit time-series data for optimal treatment.
problem Statistical methods for precision medicine in single unit time-series data.
method Adaptive sequential design, nonparametric model, double robust structure, efficient influence function.
result Valid inference for mean target parameter based on single sample.
Efficient method for choosing data points in machine learning models.
problem Choosing optimal data points for semi-supervised learning.
method Computing a 'regularity tangent' vector to measure model complexity and influence.
result The method efficiently calculates a measure of model complexity and data point influence.