MASA discovers motifs in noisy time series data.
problem Discovering common sequences of states in noisy time series data.
method MASA uses an expectation-maximization approach to solve a large optimization problem.
result MASA outperforms state-of-the-art baselines by up to 38.2%.
A new method backtracks through a few key past states to speed up credit assignment in long sequences.
problem Computational inefficiency of back-propagation through time for long sequences.
method Sparse attentive backtracking using learned attention mechanisms to skip connections.
result Matches or outperforms regular BPTT and truncated BPTT in tasks with long-term dependencies.
Introduces expected eligibility traces for more efficient credit assignment in reinforcement learning.
problem Efficiently assigning credit to states and actions in reinforcement learning.
method Introduces expected eligibility traces, allowing updates to counterfactual sequences.
result Substantial improvements in temporal-difference learning can be achieved with expected traces.
COCOA improves credit assignment in reinforcement learning by measuring contributions to rewards.
problem Improving sample efficiency in reinforcement learning through better credit assignment methods.
method Counterfactual Contribution Analysis (COCOA) for precise credit assignment.
result COCOA achieves lower bias and variance compared to Hindsight Credit Assignment (HCA), improving reinforcement learning performance.
GOAT improves graph matching speed and accuracy using optimal transport.
problem Efficiently matching large graphs in various applications.
method Replaces linear assignment with optimal transport methods.
result GOAT provides improvements in speed and accuracy.
Label assignment problems with large state spaces are important tasks especially in computer vision. Often the pairwise interaction (or smoothness prior) between labels assigned at adjacent nodes (or pixels) can be described as a function of the label difference. Exact inference in such labeling tasks is still difficul…
This paper introduces a novel clustering method using jointly learned nonlinear transforms.
problem Improving clustering performance in image data.
method A novel clustering principle based on min-max similarity/dissimilarity assignment with jointly learned nonlinear transforms.
result The method outperforms state-of-the-art clustering methods in image clustering tasks.
DPS uses posterior sampling for preference-based RL, achieving a first regret guarantee.
problem Formal frameworks for preference-based RL with theoretical analysis.
method Preference-based posterior sampling, Bayesian credit assignment.
result First asymptotic Bayesian no-regret rate for preference-based RL.
Fuses posterior distributions from different datasets using KL divergence.
problem Combining information from multiple datasets with uncertainty.
method Mean field assumption, KL divergence, assign-and-average approach.
result Efficient non-parametric algorithm for fused model computation.
The paper explores how planning with models improves credit assignment in reinforcement learning.
problem Improving credit assignment in reinforcement learning.
method Investigates the use of forward and backward models for planning in reinforcement learning.
result Establishes the relative merits and limitations of forward and backward planning mechanisms.
MACC learns communication protocols by adapting counterfactual reasoning.
problem Credit assignment and non-stationarity in communication environments.
method Adapts counterfactual reasoning to overcome credit assignment and uses action policy and Q-function of other agents to handle non-stationarity.
result MACC outperforms state-of-the-art baselines in four scenarios.
LICA learns credit assignment for cooperative agents without explicit formulation.
problem Credit assignment among cooperative agents.
method Centralized critic as hypernetwork, adaptive entropy regularization.
result Significantly outperforms previous methods on benchmarks.
A new method uses optimal transport for semi-supervised classification.
problem Semi-supervised learning with limited labeled data.
method Optimal transport formulation with Sinkhorn iteration for label assignment.
result Improved performance on CIFAR-10, CIFAR-100, and SVHN datasets compared to FixMatch.
Framework for sorting with diverse value models and valued assignment examples.
problem Sorting with diverse value models and valued assignment examples.
method Optimization model for constructing preference model from valued examples, regularization techniques, and efficient algorithm.
result Improved predictive ability and flexibility in classification performance.
A three-state model based on the Potts model is proposed to simulate financial markets. The three states are assigned to "buy", "sell" and "inactive" states. The model shows the main stylized facts observed in the financial market: fat-tailed distributions of returns and long time correlations in the absolute returns. …
A new method for few-shot learning using Laplacian regularization.
problem Few-shot learning with limited labeled data.
method Transductive Laplacian-regularized inference for feature embeddings.
result Our method outperforms state-of-the-art methods across various benchmarks.
Survive method improves model-based RL by avoiding terminal states, reducing sample complexity.
problem High sample complexity in model-free RL methods limits real-world applications.
method Introduces 'survival' concept to model-based RL, focusing on avoiding terminal states instead of maximizing rewards.
result Survive method reduces training effort by focusing on terminal states, improving model-based RL performance.
Identifies key industrial sectors in S&P 500 states.
problem Understanding changing market conditions in financial markets.
method Clustering algorithm, XAI relevance scores, Bayesian change point analysis.
result Dominant sectors (energy and IT) determine market states.
We use a semisupervised learning algorithm based on a topological data analysis approach to assign functional categories to yeast proteins using similarity graphs. This new approach to analyzing biological networks yields results that are as good as or better than state of the art existing approaches.
We propose a Bayesian expectation-maximization (EM) algorithm for reconstructing Markov-tree sparse signals via belief propagation. The measurements follow an underdetermined linear model where the regression-coefficient vector is the sum of an unknown approximately sparse signal and a zero-mean white Gaussian noise wi…
Deep learning improves cancer report classification accuracy.
problem Automatically assigning ICD-O3 codes to cancer reports.
method State-of-the-art deep learning techniques, including hierarchical and flat models, with attention mechanisms.
result Best model achieves 90.3% accuracy on topography site assignment and 84.8% on morphology type assignment.
We establish upper bounds for the minimal number of hidden units for which a binary stochastic feedforward network with sigmoid activation probabilities and a single hidden layer is a universal approximator of Markov kernels. We show that each possible probabilistic assignment of the states of n output units, given t…
Study re-evaluates MIMIC-III codes, finding many are under-coded.
problem Validity of MIMIC-III clinical codes is questionable.
method Open-source, reproducible methodology for assessing codes.
result Most frequently assigned codes are under-coded up to 35%
Multi-label classification has received considerable interest in recent years. Multi-label classifiers have to address many problems including: handling large-scale datasets with many instances and a large set of labels, compensating missing label assignments in the training set, considering correlations between labels…
Unified view on selective credit assignment for reinforcement learning.
problem Efficient credit assignment in reinforcement learning.
method Unified temporal-difference algorithms with selective weightings.
result New algorithms for backward credit assignment and off-policy learning.
Same homology via different sign assignments in link Floer theory.
problem Comparing sign assignments in link Floer homology.
method Comparison of sign assignments from two different constructions.
result Small modification of sign convention results in identical chain complexes.
CwA optimizes search performance by jointly learning a balanced database partition and a neural probing function.
problem Suboptimal search performance due to mismatched database and query distributions.
method CwA jointly learns a balanced database partition and a neural probing function to optimize search performance directly for the query distribution.
result CwA achieves up to 4.7x throughput over state-of-the-art methods at equal recall.
TextWorld is a Python library for RL agents in text-based games.
problem Training RL agents on text-based games with varying challenges and sparse rewards.
method Developed a Python library with backend functions for state tracking and reward assignment. Enables users to create new games with precise control over difficulty and scope.
result Demonstrated the effectiveness of TextWorld in training RL agents on a curated list of games and generated sets of games.
Meta-learning for efficient reward shaping in RL.
problem Challenges in designing effective reward shaping functions in RL.
method Meta-learning framework to automatically learn reward shaping on multiple tasks.
result Significantly improved learning efficiency and interpretable visualizations across various RL settings.
New method for sequential probability assignment reduces regret using contextual Shtarkov sums.
problem Minimizing regret in sequential probability assignment with arbitrary hypothesis classes.
method Introducing contextual Shtarkov sum and contextual Normalized Maximum Likelihood (cNML) algorithm.
result The contextual Shtarkov sum characterizes minimax regret and provides a minimax optimal strategy.
New pseudo-Hermitian models from non-semisimple TQFTs.
problem Constructing exactly solvable pseudo-Hermitian spin Hamiltonians.
method Identifying ground states on surfaces using non-semisimple TQFTs.
result Ground states depend only on spatial topology and can be assigned by non-semisimple TQFTs.
New algorithms assign credit to past decisions based on hindsight.
problem Efficient credit assignment in reinforcement learning.
method Explicit credit assignment using new data in hindsight.
result Value functions can be rewritten to include hindsight credit assignment.
EgalMAB solves fair resource allocation in stochastic bandits.
problem Fair resource allocation in a stochastic multi-armed bandit setting.
method Design and analysis of UCB-based policy EgalUCB.
result Established upper bounds on cumulative regret.
Continuum mechanics theory describes skin's complex anisotropic behavior.
problem Modeling the anisotropic tearing of skin.
method Finsler geometry fiber bundle approach, variational method, phase-field mechanics.
result Analytical solutions capture experimental data on skin tearing.
Assignment methods are at the heart of many algorithms for unsupervised learning and clustering - in particular, the well-known K-means and Expectation-Maximization (EM) algorithms. In this work, we study several different methods of assignment, including the "hard" assignments used by K-means and the ?soft' assignment…
Error bounds based on worst likely assignments use permutation tests to validate classifiers. Worst likely assignments can produce effective bounds even for data sets with 100 or fewer training examples. This paper introduces a statistic for use in the permutation tests of worst likely assignments that improves error b…
Sparse Attentive Backtracking selectively backpropagates long-term dependencies in recurrent networks.
problem Difficulty in learning long-term dependencies in BPTT due to computational impracticality and biased gradient estimates.
method Sparse Attentive Backtracking learns an attention mechanism over past hidden states and selectively backpropagates through high-weight paths.
result Model learns long-term dependencies with fewer backpropagation steps, addressing biased gradient issues.
New invariants for RNA foldings and stuck links defined.
problem Defining invariants for RNA foldings and stuck links.
method Assigning Boltzmann weights at classical and stuck crossings.
result Explicit computations of new invariants provided.
A celebrated theorem of Hadwiger states that the Euler-Poincaré characteristic is the the unique invariant and continuous valuation on the distributive lattice of compact polyhedra in R^n that assigns value one to each convex non-empty such polyhedron. This paper provides an analogue of Hadwiger's result for finitely p…
Meta-learning adjusts TD learning's eligibility trace parameter for more efficient reinforcement learning.
problem Efficiently tuning the eligibility trace parameter for temporal difference learning.
method Meta-learning method to adjust eligibility trace parameter state-dependently.
result Improves overall quality of update targets, minimizing target error.
Proposes Deep Fair Clustering for fair clustering with multiple protected groups.
problem Ensuring fair clustering with multiple protected groups.
method Deep Fair Clustering learns a fair cluster assignment function.
result Improves fairness while only slightly sacrificing clustering quality.
New methods optimize personalized treatment assignment in trials with many arms.
problem Poor performance of standard methods in trials with many treatment arms.
method Regularized and clustered joint assignment forest algorithm.
result Gains in predicting arm-wise outcomes and utility gains from personalization.
Proposes unbiased estimators for training mixture of experts models.
problem Efficiently training large-scale mixture of experts models on modern hardware.
method Two unbiased estimators based on principled stochastic assignment procedures.
result Both estimators are more effective and robust than biased alternatives.
New algorithm learns reward signals from episodic returns for better reinforcement learning.
problem Difficulty in designing reward functions for real-world reinforcement learning tasks.
method Introduces a new algorithm that decomposes episodic returns into time-step rewards using deep neural networks.
result Learning reward signals from episodic returns improves reinforcement learning efficiency.
Novel active learning detects network nodes for community detection.
problem Detecting community structure in networks.
method Maximal Expected Model Change (MEMC) criterion for querying network nodes.
result MEMC detects nodes that maximize community assignment likelihood changes.
Maximum a posteriori (MAP) inference over discrete Markov random fields is a fundamental task spanning a wide spectrum of real-world applications, which is known to be NP-hard for general graphs. In this paper, we propose a novel semidefinite relaxation formulation (referred to as SDR) to estimate the MAP assignment. A…
Optimizes balanced treatment assignment for experiments.
problem Balancing treatment groups in experiments for optimal results.
method Optimization of a two-sample test, using minimum spanning tree test.
result Optimal assignment algorithm with polynomial time complexity.
New results on inferring hidden states in trackable weak models.
problem Inferring hidden states in trackable weak models.
method Analyzing strongly-connected trackable weak models and reconstructing branch choices.
result The number of hypotheses in strongly-connected trackable models is bounded by a constant.