Research
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.

168,742 papers · 148 categories

Trend · papers per month

18.9%37.7%56.6%75.4% · Jun 202019922001200920172026
48 results for Learning without paired data

New method learns functions without paired data using mediating variables.

problem Learning functions without paired input-output data.
method Mediated Uncoupled Learning: Predicting h(U)h(U) to approximate YY.
result Statistical consistency and error bounds of the proposed method.

New method learns useful disentangled representations from weakly labeled data.

problem Learning useful representations from weakly labeled data.
method Model pairs of non-i.i.d. images, learn disentangled representations without requiring annotation.
result Learn disentangled representations reliably from pairs of images without requiring group, individual factor, or number of changed factors annotation.

Unified pair trading approach using hierarchical reinforcement learning.

problem Decoupling pair selection and trading leads to limited performance.
method Hierarchical reinforcement learning framework for joint pair selection and trading.
result Unified approach outperforms existing methods on real-world stock data.

cMIM improves representation learning without positive-pair augmentations.

problem Learning robust representations for diverse tasks.
method Contrastive Mutual Information Machine (cMIM) framework.
result cMIM outperforms MIM and InfoNCE on classification and regression tasks.

LLMs learn new tasks from unstructured data, but it depends on word co-occurrence and positional information.

problem Understanding how LLMs can learn new tasks from unstructured data without explicit training.
method Examined the capabilities of LLMs trained on unstructured data, focusing on sequence model requirements and training data structure.
result Many ICL capabilities can emerge from word co-occurrence in unstructured data, but positional information is crucial for certain tasks.

Proves accuracy guarantees for self-supervised learning with correlated positive pairs.

problem Lack of theoretical guarantees for self-supervised learning with correlated positive pairs.
method Novel augmentation graph concept and spectral decomposition loss.
result Provably accurate features under linear probe evaluation.

Sparse neural networks visualize paired transcriptomic and electrophysiological data.

problem Efficiently analyzing and visualizing paired multivariate neuroscientific data.
method Sparse deep neural networks with a two-dimensional bottleneck and group lasso penalty.
result Biologically interpretable two-dimensional visualizations of paired data.

We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent variable as a language agnostic representation which is encouraged to learn the meaning…

2018-06-13abs ↗pdf ↗

Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing m…

2016-12-23abs ↗pdf ↗

New method corrects motion artifacts in MR images without paired data.

problem Lack of paired data for supervised training in deep learning for MR motion correction.
method Outlier-rejecting bootstrap subsampling and aggregation, using optimal transport cycleGAN.
result Outperforms existing deep learning methods in correcting motion artifacts from TSM.

Estimating mutual information is an important statistics and machine learning problem. To estimate the mutual information from data, a common practice is preparing a set of paired samples {(xi,yi)}i=1ni.i.d.p(x,y)\{(\mathbf{x}_i,\mathbf{y}_i)\}_{i=1}^n \stackrel{\mathrm{i.i.d.}}{\sim} p(\mathbf{x},\mathbf{y}). However, in many situations, it…

2019-09-05abs ↗pdf ↗

StratLearner learns strategies to prevent misinformation in social networks.

problem Learning strategies to protect against misinformation in social networks without knowing the diffusion model.
method Structured prediction framework using random features and large margin method.
result Our method produces near-optimal protectors without diffusion model information and outperforms other methods.

We are interested in learning causal relationships between pairs of random variables, purely from observational data. To effectively address this task, the state-of-the-art relies on strong assumptions regarding the mechanisms mapping causes to effects, such as invertibility or the existence of additive noise, which on…

2014-09-15abs ↗pdf ↗

Optimizes crowdsourced preference-based subjective evaluation with online learning.

problem Large-scale evaluation of generative media using crowdsourcing due to combinatorial explosion.
method Automatic optimization of pair combination selections and evaluation volumes with online learning.
result Optimizes evaluation by reducing pair combinations and allocating optimal evaluation volumes.

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicabi…

2017-11-16abs ↗pdf ↗

Physics-informed DeepONets solve PDEs without paired data, predicting solutions quickly.

problem Lack of paired input-output data for solving PDEs.
method Physics-informed DeepONets use automatic differentiation to enforce physical laws as soft penalty constraints.
result Physics-informed DeepONets can solve PDEs without paired data, predicting solutions up to 3 orders of magnitude faster.

New method identifies causal relationships from interventions in complex systems.

problem Learning causal representations from unknown, latent interventions with general nonlinear mixing.
method Strong identifiability results with unknown single-node interventions, using geometric structure of transformed data.
result First instance of causal identifiability from non-paired interventions for deep neural network embeddings.

Entangled watermarks improve model defense against extraction attacks.

problem Model extraction attacks risk leaking valuable intellectual property.
method Entangled Watermarking Embeddings (EWE) leverages model capacity to overfit to outlier input-output pairs.
result The approach successfully claims model ownership with high confidence and minimal performance loss.

Imputation-free method learns tabular data with missing values using transformer.

problem Machine learning on tabular data with missing values often leads to unreliable outcomes due to synthetic imputation.
method Incremental attention learning (IFIAL) using transformer with attention masks.
result IFIAL outperforms state-of-the-art methods in 17 diverse tabular data sets.

The goal of this paper is to classify pairs of Morse functions in general position modulo the action of different groups.In particular, we obtain the classification of generic pairs of Morse functions, with or without target diffeomorphisms, and that of quotients of Morse functions.We will also present a lemma which gi…

2017-03-06abs ↗pdf ↗

We show that every knot type admits a pair of diagrams that cannot be made identical without using Reidemeister Omega_2-moves. We also show that our proof is compatible with known results for the other move types, in the sense that every knot type admits a pair of diagrams that cannot be made identical without using al…

2004-04-07abs ↗pdf ↗

Weak supervision enables learning causal representations from unstructured data.

problem Learning high-level causal representations from unstructured data like images.
method Weakly supervised setting with paired samples before and after interventions. Implicit latent causal models using variational autoencoders.
result Models can reliably identify causal structure and disentangle causal variables.

This paper tackles unpaired data in multi-view learning, proposing a new framework and models.

problem Handling unpaired data in multi-view learning, which is more common than paired data.
method Generalized uncorrelated multi-view subspace learning framework with successive alternating approximation (SAA) method.
result Proposed models perform competitively or better than baselines in multi-view feature extraction and multi-modality classification.

Binary feedback outperforms ordinal comparisons in ranking recovery.

problem Challenges the conventional wisdom that ordinal comparisons offer richer information.
method Proposes a parametric framework for modeling ordinal paired comparisons, binarizing ordinal data, and proving faster convergence rates for binary comparisons.
result Binarizing ordinal data significantly improves ranking recovery accuracy and exhibits a substantial performance gap.

GROOVE learns representations for weakly paired multimodal data.

problem Learning representations for high-content perturbation data with weakly paired samples.
method GroupCLIP contrastive loss integrated with an autoencoder framework.
result GROOVE performs on par with or outperforms existing approaches for cross-modal tasks.

Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training conditions. Recently, CycleGAN-VC has provided a breakthrough and performed comparably…

2019-04-09abs ↗pdf ↗

We present KERMIT, a simple insertion-based approach to generative modeling for sequences and sequence pairs. KERMIT models the joint distribution and its decompositions (i.e., marginals and conditionals) using a single neural network and, unlike much prior work, does not rely on a prespecified factorization of the dat…

2019-06-04abs ↗pdf ↗

Study perturbs APS boundary conditions for Lorentzian Dirac operators.

problem Maintaining Fredholmness of Dirac operators under perturbations of APS boundary conditions.
method Develop criteria for perturbing compact pairs of projections to remain Fredholm.
result Criteria for perturbing APS boundary conditions without losing Fredholmness.

Pessimistic Minimax Value Iteration finds efficient NE policies from offline data.

problem Finding an approximate Nash equilibrium in offline Markov games with non-uniform coverage.
method Pessimistic Minimax Value Iteration (PMVI) constructs pessimistic value function estimates and solves NEs.
result Established a nearly minimax optimal result for offline Markov games with function approximation.