On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “T-learning”

Combining T-learning and DR-learning: a framework for oracle-efficient estimation of causal contrastsstat.ML

EP-learning framework improves causal contrast estimation efficiency.

problem Estimating heterogeneous causal contrasts efficiently and stably.

method EP-learning framework combining T-learning and DR-learning.

result EP-learners are oracle-efficient and outperform competitors.

EP-learning causal contrasts T-learning DR-learning oracle efficiency

2024-02-03abs ↗pdf ↗

Analyzing limits for in-context learningstat.ML

New analysis shows transformer models can't learn effectively.

problem Transformer models learning in context can't achieve general predictive accuracy.

method Empirical evidence and mathematical analysis of transformer architecture limitations.

result Transformers cannot achieve general predictive accuracy due to architectural limitations.

transformers in-context learning predictive accuracy mathematical analysis architectural limitations

2025-02-05abs ↗pdf ↗

Positive semidefinite support vector regression metric learningcs.LG

Paper tackles multi-label learning by improving SVR for positive semidefinite metrics.

problem Learning positive semidefinite metrics for multi-label and label distribution learning.

method Proposes two methods to overcome SVR's limitation in learning positive semidefinite metrics.

result Demonstrates new methods achieve favorable performance in multi-label and label distribution learning.

metric learning SVR positive semidefinite multi-label label distribution

2020-08-18abs ↗pdf ↗

Incentivized Learning in Principal-Agent Bandit Gamesstat.ML

A study on how a principal can incentivize an agent to make better decisions in a repeated game.

problem Optimizing a principal's utility in a misaligned principal-agent bandit game.

method Developed nearly optimal learning algorithms for the principal's regret in multi-armed and linear contextual settings.

result The principal can iteratively learn an incentive policy to maximize her total utility.

incentivized learning principal-agent bandit games regret minimization mechanism design

2024-03-06abs ↗pdf ↗

Detecting Dead Weights and Units in Neural Networkscs.LG

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures trained for various problems. Weight/channel pruning, distillation, quantization, m…

2018-06-15abs ↗pdf ↗

Learning to Collaborate in Markov Decision Processescs.LG

We consider a two-agent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases when the second agent (A2) is adapting its policy in an unknown way. The key ch…

2019-01-23abs ↗pdf ↗

Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Modelscs.LG

Algorithm minimizes regret in dueling bandits with contextualized utilities.

problem Minimizing regret in dueling bandits with context-dependent utilities.

method Proposes CoLSTIM algorithm based on perturbed utility estimates.

result Achieves regret of order

ilde O(\sqrt{dT})

dueling bandits contextualized utilities regret minimization linear stochastic transitivity imputation

2022-02-09abs ↗pdf ↗

Multi-armed Bandit Learning on a Graphcs.LG

A graph bandit algorithm learns optimal paths on unknown graphs.

problem Optimal path selection on unknown graphs under uncertainty.

method G-UCB algorithm based on offline graph planning and optimism principle.

result Achieves tight regret bound of

O(\sqrt{|S|T\log(T)}+D|S|\log T)

multi-armed bandit graph bandit optimism principle regret bound graph exploration

2022-09-20abs ↗pdf ↗