arXiv research

Efficiently selects top-m designs for various contexts using sequential sampling.

Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mahé, a novel approach to provide Model-agnostic hierarchical éxplanations of how powerful machine learning models, such as deep ne…

Object ranking is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects, which are typically represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. Current approaches co…

New framework handles dynamic contexts in reinforcement learning.

The paper tackles long-context linear system identification with improved sample complexity bounds.

Choice functions accept a set of alternatives as input and produce a preferred subset of these alternatives as output. We study the problem of learning such functions under conditions of context-dependence of preferences, which means that the preference in favor of a certain choice alternative may depend on what other …

Bayesian context trees capture complex dependencies in categorical sequences.

Importance of visual context in scene understanding tasks is well recognized in the computer vision community. However, to what extent the computer vision models for image classification and semantic segmentation are dependent on the context to make their predictions is unclear. A model overly relying on context will f…

In many cases, feature selection is often more complicated than identifying a single subset of input variables that would together explain the output. There may be interactions that depend on contextual information, i.e., variables that reveal to be relevant only in some specific circumstances. In this setting, the con…

Improves TTS accuracy by correcting context-dependent units.

Contextualized ML learns context-dependent effects using deep learning.

New insights into how depth and width affect in-context learning in deep models.

We extend manifold capacity to nonlinear neural representations with contextual information.

Parallel recordings of neural spike counts have revealed the existence of context-dependent noise correlations in neural populations. Theories of population coding have also shown that such correlations can impact the information encoded by neural populations about external stimuli. Although studies have shown that the…

MQTransformer improves forecast accuracy with context-aware attention.

Proposes a new model for more accurate demand forecasting considering dynamic contextual information.

Timer-XL predicts multidimensional time series using a unified Transformer approach.

In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of context, only small amounts are considered, making it difficult to scale. We present a …

Scales attention for long contexts in LLMs.

New approach predicts tokens in context, explaining how ICL emerges.

In the classical contextual bandits problem, in each round $t$, a learner observes some context $c$, chooses some action $i$ to perform, and receives some reward $r_{i,t}(c)$. We consider the variant of this problem where in addition to receiving the reward $r_{i,t}(c)$, the learner also learns the values of $r_{i,t}(c…

Enhances activity recognition in wearable computing with context awareness and uncertainty quantification.

Transformers learn rich in-context dependencies efficiently.

We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts. The new model, called Contextual Markov Decision Process (CMDP), can model a cu…

A two-step approach efficiently selects hyperparameters for FCMs.

Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-le…

New techniques save bits in image compression with upsampling.

CausalRegNet generates accurate data for gene perturbation experiments, improving CSL methods.

Direct approach for handling contextual bandits with latent state dynamics.

Algorithm minimizes regret in dueling bandits with contextualized utilities.

Paper proves tight lower bounds for online multicalibration, separating it from marginal calibration.

We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into …

Decodes neural activity to detect context effects in natural settings.

The paper examines how small positive dependence can lead to correlated tail risks.

LLMs compress financial texts, but distort decision-making.

Proposes a new model for context-dependent decision-making.

In this paper we propose the multi-objective contextual bandit problem with similarity information. This problem extends the classical contextual bandit problem with similarity information by introducing multiple and possibly conflicting objectives. Since the best arm in each objective can be different given the contex…

Transformers learn low-dimensional target functions efficiently in-context.

This work introduces RISE to explain LLMs more reliably by distinguishing essential context.

There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence. In this work, we show for the first time t…

Paper proposes linear transformers for efficient in-context learning without context length limitations.

New algorithm reduces regret in noisy context bandits.

To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-ba…

Researchers analyze neural process architectures and their representational capacities.

Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an extreme diversity space, such as \textit{person-behind-person} and \textit{car-behind…

NOTMAD estimates context-specific Bayesian networks without breaking datasets.

Introduces CStrees for modeling context-specific causal models from observational and interventional data.

Dirichlet processes (DP) are widely applied in Bayesian nonparametric modeling. However, in their basic form they do not directly integrate dependency information among data arising from space and time. In this paper, we propose location dependent Dirichlet processes (LDDP) which incorporate nonparametric Gaussian proc…