The paper analyzes sports commentary to automatically recognize events and extract insights.
problem Automatically recognizing and categorizing major actions in sports events from commentary.
method Used multiple Natural Language Processing techniques for classification and sentiment analysis.
result Identified insights from analyzing live sport commentaries and classifying major actions.
LLM extracts actionable insights from customer reviews.
problem Extracting actionable insights from customer reviews.
method Large language model approach distinguishing perceptual attributes from actionable features.
result High consistency and predictive validity of LLM insights compared to human coders.
Extends T-duality to non-principal torus actions with elliptic tangent bundles.
problem Classifying and understanding non-principal torus actions with singularities.
method Introduces elliptic tangent bundle to control singularities, uses it to define connections and transport generalized complex structures via T-duality.
result New insights into the classification of torus actions and transport of generalized complex structures.
Paper simplifies complex sports analytics models for better understanding.
problem Difficulty in interpreting deep learning models for sports analytics.
method Developed a linear model tree that mimics deep learning models and explains its knowledge.
result The linear model tree achieves high accuracy and provides actionable insights.
New insights into surface group actions and entropy.
problem Understanding proper affine actions of surface groups.
method Explicit neighborhoods in quasifuchsian space and critical points of entropy.
result Critical points of entropy lie on the Fuchsian locus.
New insights into the geometry of flows on 3-manifolds.
problem Understanding the geometry of flows on 3-manifolds.
method Analyzing the action of pseudo-Anosov flows on Gromov-hyperbolic spaces.
result Genericity of non-periodic elements in the fundamental group.
The paper investigates the effects of invalid action masking in policy gradient algorithms.
problem Invalid actions in policy gradient algorithms can lead to suboptimal performance.
method The paper provides theoretical justification and empirical demonstrations of the importance of invalid action masking.
result Invalid action masking is crucial as the number of invalid actions increases.
A new calibration metric bridges testability and actionability.
problem Combining testability and actionable insights for forecast probabilities.
method Cutoff Calibration Error (CCE) that assesses calibration over intervals of forecasted probabilities.
result Cutoff Calibration Error is both testable and actionable.
SHIFT framework identifies subgroups with large ML model performance decay.
problem Large model performance decay in subgroups when deployed.
method Subgroup-scanning Hierarchical Inference Framework (SHIFT) for performance drift.
result SHIFT identifies interpretable subgroups with large performance decay and suggests targeted actions to mitigate it.
Novel IRL method identifies suboptimal medical decisions in ICU data.
problem Identifying suboptimal medical decisions in clinical settings.
method Incorporates Inverse Reinforcement Learning with a pruning step to identify and remove suboptimal actions.
result Pruning step effectively identifies clinical priorities and values from suboptimal data.
New insights into symplectic loops and their flux groups.
problem Understanding symplectic loops and their properties.
method Analyzing symplectic diffeomorphisms and their orbits.
result Flux of symplectic loops vanishes for contractible orbits.
New insights into symplectic singularities via canonical torus actions.
problem Understanding symplectic singularities and their actions.
method Use of (C∗)r actions and Donaldson-Sun theory. result Symplectic singularities admit canonical (C∗)r actions. Computational results demonstrate that posterior sampling for reinforcement learning (PSRL) dramatically outperforms algorithms driven by optimism, such as UCRL2. We provide insight into the extent of this performance boost and the phenomenon that drives it. We leverage this insight to establish an $\tilde{O}(H\sqrt{SA…
Classifies actions of groups on hyperbolic spaces, proving dichotomy.
problem Classifying actions of groups on hyperbolic spaces.
method Formalization using Borel equivalence relations, focusing on non-elementary actions without fixed points at infinity.
result For every countable group G, either all general type actions can be classified by an explicit invariant or they are unclassifiable in a strong sense. New findings show optimization is crucial for OPL in large action spaces.
problem Challenges in optimizing policies for large action spaces in offline contextual bandits.
method Weighed log-likelihood objectives and estimator-aware policy parametrization.
result Simple weighted log-likelihood objectives enjoy better optimization properties and recover competitive policies.
Analyzes retail trends from sales, search, and reviews.
problem Optimizing inventory and marketing for better customer satisfaction.
method Historical sales data, search trends, and customer reviews.
result Identifies patterns and trending products for retailers.
Study reveals hidden infections and infection dynamics from early data.
problem Understanding early infection dynamics and hidden infections in COVID-19.
method Data-driven machine learning analysis focusing on infection counts over time.
result Significant asymptomatic infections, 10-day lag, and strong infectious force.
Action chunking and data exploration improve behavior cloning in robotics.
problem Exponential errors in learning from demonstrations for continuous control tasks.
method Action chunking and exploratory data collection.
result Control-theoretic stability is key to improving imitation learning.
Q-chunking improves RL for long tasks by chunking actions.
problem Improving sample efficiency and exploration in offline-to-online RL.
method Action chunking in TD-based RL methods.
result Q-chunking outperforms prior methods on long-horizon tasks.
This study uses AI to analyze financial market coverage from YouTube videos.
problem Challenges in analyzing a large number of financial market videos.
method Used Whisper model to generate text from videos, applied natural language processing.
result Highlights dynamics of financial market coverage and identifies trending topics.
CFRecs uses counterfactual reasoning to improve graph-based recommendations in real estate.
problem Improving model interpretability and actionable insights in graph-based recommender systems.
method A two-stage architecture combining GNN and Graph-VAE to propose minimal yet impactful changes in graph structure and node attributes.
result Demonstrates effectiveness in delivering actionable recommendations for home buyers and sellers.
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding oth…
Decouples critic chunk length from policy to improve policy reactivity and performance.
problem Bootstrapping bias and difficulty in extracting optimal policies from chunked critics.
method Optimizes policy against a distilled critic for partial action chunks, allowing shorter chunks for policy.
result Reliably outperforms prior methods on long-horizon offline goal-conditioned tasks.
Framework improves health by planning actionable treatment processes.
problem Developing objective treatment processes in clinical settings.
method Surrogate Bayesian model combined with ML for personalized health improvement.
result Computed treatment processes are actionable and consistent with clinical knowledge.
A new method uses algebraic insights to create approximately equivariant networks without complex architectures.
problem Designing equivariant neural networks with complex architectures and high computational cost.
method Imposes the group's regular representation as an inductive bias via an auxiliary loss, adding no learnable parameters.
result Matches or outperforms specialized models in several cases, even for infinite groups.
We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to evaluate what would happen if different actions were taken in the same contexts, so …
BRACE generates efficient counterfactual explanations by integrating causal reasoning.
problem Challenges in traditional counterfactual explanations, especially neglecting causal relationships.
method Backtracking counterfactuals with causal reasoning.
result Our method provides deeper insights into model outputs and is computationally efficient.
We introduce a method by which a generative model learning the joint distribution between actions and future states can be used to automatically infer a control scheme for any desired reward function, which may be altered on the fly without retraining the model. In this method, the problem of action selection is reduce…
Paper proposes a framework to assess model robustness against adversarial actions.
problem Ensuring model reliability in deployment with varied adversarial conditions.
method Developed a versatile framework for evaluating SVR and relaxed optimization models' robustness.
result Demonstrates model vulnerability without requiring additional test data.
We construct a mathematical framework for twisted N=2 supersymmetric topological quantum field theory on a 4-manifold. Supersymmetry in flat space is defined and the twist homomorphism is constructed, giving us a supermanifold that is the total space of an odd vector bundle over the even 4-manifold. A special category …
User intended actions are widely seen in many areas. Forecasting these actions and taking proactive measures to optimize business outcome is a crucial step towards sustaining the steady business growth. In this work, we focus on pre- dicting attrition, which is one of typical user intended actions. Conventional attriti…
Mid-training improves RL by identifying compact action abstractions.
problem Unlocking full potential of RL with large language models.
method RA3 algorithm that optimizes sequential variational lower bound and discovers latent structures via RL.
result Improves performance by 8 points on HumanEval and 4 points on MBPP.
Robustness of Deep Reinforcement Learning (DRL) algorithms towards adversarial attacks in real world applications such as those deployed in cyber-physical systems (CPS) are of increasing concern. Numerous studies have investigated the mechanisms of attacks on the RL agent's state space. Nonetheless, attacks on the RL a…
While mobile social apps have become increasingly important in people's daily life, we have limited understanding on what motivates users to engage with these apps. In this paper, we answer the question whether users' in-app activity patterns help inform their future app engagement (e.g., active days in a future time w…
New algorithm balances exploration cost between groups in multi-armed bandits.
problem Balancing exploration cost between groups in multi-armed bandits.
method Introducing Col-UCB algorithm that dynamically coordinates exploration across groups.
result Achieves optimal minimax and instance-dependent collaborative regret up to logarithmic factors.
Study detects and explains positional bias in financial LLMs.
problem Positional bias in financial decision-making using LLMs.
method Unified framework and benchmark for detecting and quantifying bias in Qwen2.5 models.
result Positional bias is pervasive, scale-sensitive, and resurfaces under nuanced prompt designs.
Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this infer…
Active inference selects actions to maximize information gain, aiding structure learning.
problem Learning the structure of underlying world models.
method Active inference selects actions based on expected free energy, which includes information gain and value.
result Actions that maximize information gain help disambiguate among alternative models.
For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning methods stop at the first step, providing practitioners with insight into a model, but…
Optimizes Thompson sampling policies using policy gradient methods.
problem Improving Thompson sampling in bandit problems.
method Applies policy gradient algorithms to optimize Thompson sampling policies.
result Direct policy search on Thompson sampling improves performance.
We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge. The BAMDP framework elegantly addresses model uncertainty by incorporating Bayesian belief updates into long-term expected return. However, computing an e…
Develops methods for finding counterfactual explanations in sequential decision making.
problem Finding counterfactual explanations for sequential decision making processes.
method Formal characterization of sequential actions and states using Markov decision processes and Gumbel-Max structural causal model. Introduces a polynomial time algorithm based on dynamic programming.
result Algorithm finds optimal counterfactual explanations for sequential decision making.
Study how untrained policies explore in RL environments.
problem Challenges in reinforcement learning, especially sparse or adversarial reward structures.
method Theoretical and empirical analysis of untrained deep neural policies in a toy model.
result Untrained policies generate correlated actions and non-trivial state-visitation distributions.
FinGPT uses LLMs for real-time market sentiment analysis.
problem Real-time market sentiment analysis for trading.
method Synthesizes financial news and social media data, integrates with technical indicators, uses FinGPT for sentiment analysis.
result Generates actionable trading signals using LLMs.
This work proposes a geometric approach to equivariant message passing on Riemannian manifolds.
problem Efficiently processing data on Riemannian manifolds with equivariance.
method Geometric insight into equivariant message passing on Riemannian manifolds, using an equivariant embedding and diffusion process.
result A new class of equivariant GNNs on Riemannian manifolds.
Develops a dynamic mean field theory for reinforcement learning.
problem Finite state and action Bayesian reinforcement learning in large state spaces.
method Analogies with statistical physics, interpreting probabilities as couplings and values as spins, solving mean field equations.
result State-action values are statistically independent in the asymptotic state space limit, with exact or approximate equations for computation.
Twitter, a popular social network, presents great opportunities for on-line machine learning research. However, previous research has focused almost entirely on learning from passively collected data. We study the problem of learning to acquire followers through normative user behavior, as opposed to the mass following…
Study shows how to learn optimal policies quickly in stochastic control problems.
problem Learning optimal policies in large, continuous state and action spaces with limited data.
method Analyzes three geometric exponents to quantify fast policy regret convergence.
result Shows that fast policy regret convergence is induced by specific geometric structures.