FlowVAT improves variational inference for multi-modal distributions.
problem Mode-seeking behavior and collapse in variational inference for complex posteriors.
method Conditional tempering approach for normalizing flow variational inference.
result FlowVAT outperforms traditional and adaptive annealing methods in multi-modal distributions, finding more modes and achieving better ELBO values.
New method trains neural samplers to sample from multi-modal distributions efficiently.
problem Mode-seeking behavior of reverse KL divergence hinders effective sampling from multi-modal target distributions.
method Minimizing reverse diffusive KL divergence along diffusion trajectories of model and target densities.
result Demonstrated enhanced sampling performance across various multi-modal distributions.
In this paper, we propose a new fuzzy clustering algorithm based on the mode-seeking framework. Given a dataset in Rd, we define regions of high density that we call cluster cores. We then consider a random walk on a neighborhood graph built on top of our data points which is designed to be attracted by hig…
Paper tackles offline RL from mixed datasets with adaptive KL regularizer.
problem Challenges in optimizing RL and BC signals with varying action coverage and multiple action modes.
method Adaptively weighted reverse KL divergence regularizer based on TD3 algorithm.
result Empirically outperforms existing offline RL algorithms in MuJoCo locomotion tasks.
CADD improves generative quality by augmenting discrete diffusion with continuous latent space.
problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.
Modes and ridges of the probability density function behind observed data are useful geometric features. Mode-seeking clustering assigns cluster labels by associating data samples with the nearest modes, and estimation of density ridges enables us to find lower-dimensional structures hidden in data. A key technical cha…
CT compares two distributions using Bayes' theorem and chain rule.
problem Measuring the difference between two probability distributions.
method Conditional transport (CT) using chain rule and Bayes' theorem.
result CT strikes a good balance between mode-covering and mode-seeking behaviors.
Quick Shift is a popular mode-seeking and clustering algorithm. We present finite sample statistical consistency guarantees for Quick Shift on mode and cluster recovery under mild distributional assumptions. We then apply our results to construct a consistent modal regression algorithm.
A significantly faster algorithm is presented for the original kNN mode seeking procedure. It has the advantages over the well-known mean shift algorithm that it is feasible in high-dimensional vector spaces and results in uniquely, well defined modes. Moreover, without any additional computational effort it may yield …
The paper examines the sampling dynamics of diffusion models using ODEs.
problem Understanding the sampling dynamics of diffusion models.
method Careful inspection of ODE-based sampling of SDEs, revealing structures and relationships.
result Established a theoretical relationship between optimal ODE-based sampling and mean-shift algorithm.
EM Distillation simplifies diffusion models to one-step generators.
problem Efficient sampling from complex diffusion models with minimal loss of quality.
method EM Distillation, a maximum likelihood approach based on Expectation-Maximization.
result EM Distillation outperforms existing one-step generative methods in FID scores.
HypeGBMS clusters data in hyperbolic space, overcoming Euclidean limitations.
problem Clustering in hierarchical or tree-like datasets in curved spaces.
method Hyperbolic Gaussian Blurring Mean Shift with Möbius-weighted means.
result HypeGBMS effectively captures latent hierarchies in non-Euclidean data.
New framework improves variational inference for high-dimensional posteriors.
problem Challenges in choosing variational objectives and approximating families for high-dimensional posteriors.
method Conceptual framework and experimental tools to understand and optimize variational objectives and families.
result For moderate-to-high-dimensional posteriors, exclusive KL divergence is recommended due to optimization ease; for low-dimensional, heavy-tailed variational families are effective.
Flow AIS Bootstrap improves flow training by generating samples in hard-to-reach regions.
problem Training flows with high variance and mode-seeking behavior.
method Augment flows with AIS and minimize α-divergence with α=2. result FAB learns Boltzmann distribution of alanine dipeptide without MD samples.
Given i.i.d samples from some unknown continuous density on hyper-rectangle [0,1]d, we attempt to learn a piecewise constant function that approximates this underlying density non-parametrically. Our density estimate is defined on a binary split of [0,1]d and built up sequentially according to discrepancy crite…
FAB combines flows with AIS to approximate complex distributions.
problem Challenges in flow-based methods, especially on complex targets.
method Combines flows with AIS, using α-divergence for training.
result FAB produces accurate approximations to complex distributions.
Develops an MS-inspired algorithm for regression mode finding and space partitioning.
problem Finding local modes of regression functions and partitioning input space.
method Mean-shift-inspired algorithm for iterative gradient ascent.
result Proves convergence and rates of convergence for estimated local modes.
Log-density gradient estimation is a fundamental statistical problem and possesses various practical applications such as clustering and measuring non-Gaussianity. A naive two-step approach of first estimating the density and then taking its log-gradient is unreliable because an accurate density estimate does not neces…
Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models
problem Bayesian Optimization
method Bayesian Optimization with Conditional Diffusion Models
result DMS outperforms standard BO baselines
A new method improves posterior approximation for complex distributions.
problem Difficulty in capturing multimodal and heavy-tailed posteriors with standard normalizing flows.
method StiCTAF: stick-breaking mixture base with component-wise tail adaptation.
result Improved tail recovery and better mode coverage compared to benchmarks.
ADPO optimizes relative advantage in reinforcement learning from human feedback.
problem Optimizing policy alignment in reinforcement learning from human preferences.
method ADPO explicitly parameterizes the optimal structure through anchored logits, decoupling response quality from prior popularity.
result Empirically, ADPO achieves state-of-the-art performance on reasoning tasks, outperforming GRPO by 30.9 percent.
We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often …
Applying probabilistic models to reinforcement learning (RL) enables the application of powerful optimisation tools such as variational inference to RL. However, existing inference frameworks and their algorithms pose significant challenges for learning optimal policies, e.g., the absence of mode capturing behaviour in…
End-to-end learnable Gaussian mixture priors improve diffusion models' exploration and expressiveness.
problem Challenges in diffusion models when priors differ from target distributions.
method End-to-end learnable Gaussian mixture priors (GMPs) with iterative refinement.
result Significant performance improvements across various benchmark problems.
Mean shift clustering finds the modes of the data probability density by identifying the zero points of the density gradient. Since it does not require to fix the number of clusters in advance, the mean shift has been a popular clustering algorithm in various application fields. A typical implementation of the mean shi…
A feature-weighted mean shift algorithm improves clustering in high-dimensional data.
problem Clustering high-dimensional data with traditional mean shift algorithms.
method Feature-weighted mean shift algorithm.
result The algorithm outperforms conventional mean shift and preserves computational simplicity.
FTIP uses normalizing flows to improve posterior inference in function space.
problem Challenges in posterior inference with implicit-process priors.
method FTIP uses normalizing flows to define a richer variational distribution over combination weights.
result FTIP captures asymmetric and multimodal posterior structure better than Gaussian coefficient approximations.
A new mathematical framework for multimodal learning.
problem Linking different data modalities for better understanding.
method Interpreting contrastive learning as optimizing encoders for conditional probability distributions.
result Novel probabilistic loss functions and metrics for alignment in latent space.
Model captures neural activity related to behavior while separating internal computations.
problem Capturing neural activity related to behavior from complex brain recordings.
method Behavior-decomposed linear dynamical systems (b-dLDS) model.
result Improves over state-of-the-art models in disentangling behavior-related dynamics.
Behavior modification improves prediction accuracy by nudging user behavior.
problem Improving prediction accuracy using behavior modification techniques.
method Combining prediction and behavior modification with reinforcement learning algorithms.
result Behavior modification can make predictions more certain but may not generalize.
LISBET automates social behavior analysis using machine learning.
problem Manual annotation of social behaviors is time-consuming, biased, and misses subtle interactions.
method Self-supervised learning on body tracking data.
result Automated detection and segmentation of social interactions.
The paper introduces new metrics for evaluating generative models of behavior.
problem Lack of quantitative evaluation criteria for unsupervised behavior discovery.
method Proposed and investigated several metrics for generative models of behavior.
result The proposed metrics correspond with biologists' intuitions and allow for model evaluation and bias understanding.
Mobile phones can record individual's daily behavioral data as a time-series. In this paper, we present an effective time-series segmentation technique that extracts optimal time segments of individual's similar behavioral characteristics utilizing their mobile phone data. One of the determinants of an individual's beh…
Study reveals LLM personality patterns but lacks behavioral consistency.
problem Understanding and validating personality traits in LLMs.
method Characterized LLM personality across three dimensions: training dynamics, self-report validity, and intervention effects.
result Self-reported traits do not reliably predict behavior, and instructional alignment affects trait expression but not behavior.
Herd behavior is an important economic phenomenon, especially in the context of the recent financial crises. In this paper, herd behavior in global stock markets is investigated with a focus on intercontinental comparison. Since most existing herd behavior indices do not provide a comparative method, we propose a new h…
Interactive news recommendation has been launched and attracted much attention recently. In this scenario, user's behavior evolves from single click behavior to multiple behaviors including like, comment, share etc. However, most of the existing methods still use single click behavior as the unique criterion of judging…
Study examines if LLMs' trading styles match real market behavior.
problem Lack of behavioral consistency in LLMs' trading strategies.
method Year-long simulations with LLMs, operationalizing behavioral finance drivers, and comparing with financial theory.
result LLMs' strategy switching is only partially consistent with behavioral finance theories.
A test measures artificial agents' human-like behavior in video games.
problem Measuring the believability of artificial agents' human-like behavior.
method Developed a non-parametric two-sample hypothesis test.
result The p-value correlates with human judgment of human-like behavior. Method uses DNNs to approximate functions with specific asymptotic behavior.
problem Approximating functions with given asymptotic behavior.
method Specifically constructed terms combined with unconstrained DNN.
result Enforcing asymptotic behavior leads to better approximation and faster convergence.
Study models Ricci flow on complex surfaces, showing mixed behavior.
problem Understanding long-time behavior of Ricci flow on complex surfaces.
method BiLipschitz models for 4-manifolds (minimal surfaces of general type).
result Exhibits a combination of expanding and static behavior.
Model predicts human food choices based on demographics.
problem Predicting human food choices from demographic data.
method Non-deterministic model based on NHANES dataset and behavioral studies.
result Generates synthetic data similar to original dataset.
We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-policy returns to account…
Paper develops a framework for learning interpretable representations of sequential decision behavior.
problem Obtaining a transparent description of existing behavior.
method Inverse decision modeling framework, formalizing both forward and inverse problems.
result Learning interpretable representations of behavior, including suboptimal actions, biased beliefs, and imperfect knowledge.
Study uses contrastive learning to analyze market order behavior.
problem Understanding diverse market order behaviors.
method Self-supervised learning with triplet loss for order representation.
result Identified distinct behavior types using K-means clustering.
Collective behavior of the complex socio-economic systems is heavily influenced by the herding, group, behavior of individuals. The importance of the herding behavior may enable the control of the collective behavior of the individuals. In this contribution we consider a simple agent-based herding model modified to inc…
Study asymptotic behaviors of solutions near singular boundaries for the Yamabe problem.
problem Boundary behavior of the singular Yamabe problem near singular boundaries.
method Analysis of asymptotic behaviors and derivation of optimal estimates for background metrics.
result Solutions are well approximated by solutions in tangent cones at singular points.
We propose Turing Learning, a novel system identification method for inferring the behavior of natural or artificial systems. Turing Learning simultaneously optimizes two populations of computer programs, one representing models of the behavior of the system under investigation, and the other representing classifiers. …
Study uses ML to analyze financial behavior in big data.
problem Challenges in analyzing financial big data.
method Applied machine learning to financial behavioral data.
result ML models can effectively estimate performance in financial markets.