arXiv research

Corrected a mistake in a paper about minimal surfaces.

Paper tackles graph matching with partially correct seeds, improving performance guarantees.

The paper corrects a proof and extends a theorem about linking pairings in 4-manifolds.

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the observations are high-dimensional (e.g. images). For this reason, previous works have…

SCaSML improves PDE solvers by correcting errors efficiently.

PPI uses predictions and weighting to infer from partially labeled data.

SA-PEF improves federated learning efficiency by correcting gradient mismatches.

Develops a theory for equivariant networks with partial domain symmetry.

Partial soft-matching distance improves neural representation comparison by allowing some neurons to remain unmatched.

Paper tackles blind polynomial regression for unknown inputs.

Corrected Monti's blow-up analysis for H-minimizing sets in Heisenberg group.

Corrected graph convolutions improve node classification on graphs.

Corrects a 1998 proof about free factors of free groups.

Čech cohomology $H^n(X)$ of a separable metrizable space $X$ is defined in terms of cohomology of its nerves (or ANR neighborhoods) $P_β$ whereas Steenrod-Sitnikov homology $H_n(X)$ is defined in terms of homology of compact subsets $K_α\subset X$. We show that one can also go vice versa: in a sense, $H^n(X)$ can be re…

Partial monitoring is a generalization of the well-known multi-armed bandit framework where the loss is not directly observed by the learner. We complete the classification of finite adversarial partial monitoring to include all games, solving an open problem posed by Bartok et al. [2014]. Along the way we simplify and…

Proposes PA-DSL for correcting noisy human labels in automated data labeling.

We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite horizon context for off-policy policy evaluation. We propose estimated mixture policy …

Partial Label Learning (PLL) aims to learn from the data where each training example is associated with a set of candidate labels, among which only one is correct. The key to deal with such problem is to disambiguate the candidate label sets and obtain the correct assignments between instances and their candidate label…

While computer and communication technologies have provided effective means to scale up many aspects of education, the submission and grading of assessments such as homework assignments and tests remains a weak link. In this paper, we study the problem of automatically grading the kinds of open response mathematical qu…

A lightweight framework improves convergence and stability of PINNs for complex PDEs.

This paper is concerned with the following Markovian stochastic differential equation of mean-reversion type \[ dR_t= (θ+σα(R_t, t))R_t dt +σR_t dB_t \] with an initial value $R_0=r_0\in\mathbb{R}$, where $θ\in\mathbb{R}$ and $σ>0$ are constants, and the mean correction function $α:\mathbb{R}\times[0,\infty)\to α(x,t)\…

Partial recovery of node mappings between correlated graphs is possible under specific conditions.

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have been developed for this problem, recent challenging real-world applications require further performance…

We propose a new approach to address the text classification problems when learning with partial labels is beneficial. Instead of offering each training sample a set of candidate labels, we assign negative-oriented labels to the ambiguous training examples if they are unlikely fall into certain classes. We construct ou…

Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either simply treating each candidate label equally or iteratively identifying the true…

We consider the mean-variance hedging problem under partial Information. The underlying asset price process follows a continuous semimartingale and strategies have to be constructed when only part of the information in the market is available. We show that the initial mean variance hedging problem is equivalent to a ne…

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with partially labeled examples. Specifically, we propose a unified formulation with pro…

Machine learning offers novel ways and means to design personalized learning systems wherein each student's educational experience is customized in real time depending on their background, learning goals, and performance to date. SPARse Factor Analysis (SPARFA) is a novel framework for machine learning-based learning a…

LLMs struggle with zero-shot annotation tasks due to model-internalized priors.

Efficiently learns from partial labels using variational inference.

Community detection was a hot topic on network analysis, where the main aim is to perform unsupervised learning or clustering in networks. Recently, semi-supervised learning has received increasing attention among researchers. In this paper, we propose a new algorithm, called weighted inverse Laplacian (WIL), for predi…

Midicoth compresses online probability estimates by correcting prior smoothing biases.

Algorithm identifies optimal stable matching in uncertain two-sided markets.

We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…

Recently, there has been significant interest in linear regression in the situation where predictors and responses are not observed in matching pairs corresponding to the same statistical unit as a consequence of separate data collection and uncertainty in data integration. Mismatched pairs can considerably impact the …

Neural operators correct PDE residuals to improve BIP solutions.

Efficient surrogate modeling for complex PDEs with physical laws.

Improved latent dynamics identification framework reduces training time and improves accuracy.

FedSGM tackles constrained federated learning with unified framework.

In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into $3 \times 3$ batches and uses a hierarchy of Hamming Weight Compressors to …

Calibrated PRMs improve inference efficiency for LLMs by dynamically adjusting compute budgets.

DC3 uses deep learning to solve hard-constrained optimization problems efficiently.

New method uses Gaussian processes for solving linear PDEs with boundary conditions.

Polyhedra collapse to subpolyhedra if they can be continuously shrunk onto them.

Improved model error correction online with neural networks in 4D-Var.

Researchers formalize PD and PFI to relate them to data generating process.

A new RL method improves revenue management with delayed feedback.

We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set. Our algorithm combines reinforcement learning and end-to-end imita…