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.
Contrastive embeddings improve neural architecture search performance.
Adaptive contrastive search improves text generation quality and diversity.
Fast approximate nearest neighbor (NN) search in large databases is becoming popular. Several powerful learning-based formulations have been proposed recently. However, not much attention has been paid to a more fundamental question: how difficult is (approximate) nearest neighbor search in a given data set? And which …
Improved similarity search in embeddings using InfoNCE loss.
GCBS improves contrastive learning performance efficiently.
MICO uses mutual information co-training to improve selective search efficiency.
Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.
Teaches an active learner with contrastive examples to speed up learning.
GAMA is a user-friendly AutoML system for machine learning pipeline optimization.
We introduce "Search with Amortized Value Estimates" (SAVE), an approach for combining model-free Q-learning with model-based Monte-Carlo Tree Search (MCTS). In SAVE, a learned prior over state-action values is used to guide MCTS, which estimates an improved set of state-action values. The new Q-estimates are then used…
Improves neural network search in combinatorial spaces of mathematical symbols.
New methods use vector search and nearest-neighbor matching for policy learning in causal inference.
Bayesian graph contrastive learning improves uncertainty quantification for graph analytics.
We introduce the use of a Gated Recurrent Unit (GRU) for influenza prediction at the state- and city-level in the US, and experiment with the inclusion of real-time flu-related Internet search data. We find that a GRU has lower prediction error than current state-of-the-art methods for data-driven influenza prediction …
A new scheme reduces global search cost by a square root factor.
Bayesian methods improve drug discovery experiment design.
Space-filling designs such as scrambled-Hammersley, Latin Hypercube Sampling and Jittered Sampling have been proposed for fully parallel hyperparameter search, and were shown to be more effective than random or grid search. In this paper, we show that these designs only improve over random search by a constant factor. …
The growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of automated methods for neural architecture search. The choice of the network architecture has proven to be critical, and many advances in deep learning spring from its immediate im…
DC-NAS improves neural architecture search by clustering and evaluating sub-networks.
Unified framework connects EI and information-theoretic acquisition functions.
Autonomous systems can be used to search for sparse signals in a large space; e.g., aerial robots can be deployed to localize threats, detect gas leaks, or respond to distress calls. Intuitively, search algorithms may increase efficiency by collecting aggregate measurements summarizing large contiguous regions. However…
Independent component analysis (ICA) aims at decomposing an observed random vector into statistically independent variables. Deflation-based implementations, such as the popular one-unit FastICA algorithm and its variants, extract the independent components one after another. A novel method for deflationary ICA, referr…
New measure assesses time series pre-training data quality without labels.
Discovering causal structure among a set of variables is a fundamental problem in many empirical sciences. Traditional score-based casual discovery methods rely on various local heuristics to search for a Directed Acyclic Graph (DAG) according to a predefined score function. While these methods, e.g., greedy equivalenc…
In this paper, we propose an efficient algorithm for mining novel `Set of Contrasting Rules'-pattern (SCR-pattern), which consists of several association rules. This pattern is of high interest due to the guaranteed quality of the rules forming it and its ability to discover useful knowledge. However, SCR-pattern has n…
The paper studies how search and distillation improve reasoning in large language models.
HAMD optimizes cubic portfolios without quadratization, achieving better results.
CAPITAL algorithm identifies optimal patient subgroups for better treatment.
Decoding strategies often exclude human-like tokens, creating a detectable gap in generated text.
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
In recent years an increasing number of researchers and practitioners have been suggesting algorithms for large-scale neural network architecture search: genetic algorithms, reinforcement learning, learning curve extrapolation, and accuracy predictors. None of them, however, demonstrated high-performance without traini…
The recent advent of automated neural network architecture search led to several methods that outperform state-of-the-art human-designed architectures. However, these approaches are computationally expensive, in extreme cases consuming GPU years. We propose two novel methods which aim to expedite this optimization prob…
New algorithm reduces sample complexity for planning in MDPs.
Learning rate annealing improves robustness in stochastic optimization.
PARMESAN learns from memory without parameters for fast, efficient continual learning.
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
The fruit fly Drosophila's olfactory circuit has inspired a new locality sensitive hashing (LSH) algorithm, FlyHash. In contrast with classical LSH algorithms that produce low dimensional hash codes, FlyHash produces sparse high-dimensional hash codes and has also been shown to have superior empirical performance compa…
We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and…
Optimal decision trees learned via dynamic programming and search.
GCC pre-trains graph neural networks to transfer across diverse datasets.
Study improves policy search in continuous control by using heavy-tailed distributions.
We consider the problem of learning a forest of nonlinear decision rules with general loss functions. The standard methods employ boosted decision trees such as Adaboost for exponential loss and Friedman's gradient boosting for general loss. In contrast to these traditional boosting algorithms that treat a tree learner…
Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually departs from some notion of similarity, comparing two enzymes by looking for correspondences in their sequences, structures or surfaces. For a…
DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints bet…
DL/FBF improves GPSR solutions by selecting compact, generalising expressions.
In standard graph clustering/community detection, one is interested in partitioning the graph into more densely connected subsets of nodes. In contrast, the "search" problem of this paper aims to only find the nodes in a "single" such community, the target, out of the many communities that may exist. To do so , we are …
Unknown constraints arise in many types of expensive black-box optimization problems. Several methods have been proposed recently for performing Bayesian optimization with constraints, based on the expected improvement (EI) heuristic. However, EI can lead to pathologies when used with constraints. For example, in the c…
BOBYQA optimizes deep networks with fewer queries than other methods.