Related papers: Just Train Twice: Improving Group Robustness witho…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…

Machine learning models can fail on subgroups that are underrepresented during training. While techniques such as dataset balancing can improve performance on underperforming groups, they require access to training group annotations and can…

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language…

Regularization plays a vital role in machine learning optimization. One novel regularization method called flooding makes the training loss fluctuate around the flooding level. It intends to make the model continue to random walk until it…

We study the problem of excess risk evaluation for empirical risk minimization (ERM) under convex losses. We show that by leveraging the idea of wild refitting, one can upper bound the excess risk through the so-called "wild optimism,"…

We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the…

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative…

In this paper, we investigate the empirical counterpart of Group Distributionally Robust Optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups. We formulate empirical GDRO as a…

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric…

The cardinality estimation is a key aspect of query optimization research, and its performance has significantly improved with the integration of machine learning. To overcome the "cold start" problem or the lack of model transferability in…

In settings where both spurious and causal predictors are available, standard neural networks trained under the objective of empirical risk minimization (ERM) with no additional inductive biases tend to have a dependence on a spurious…

In many machine learning tasks, known symmetries can be used as an inductive bias to improve model performance. In this paper, we consider learning group equivariance through training with data augmentation. We summarize results from a…

Reliability in cell type annotation is challenging in single-cell RNA-sequencing data analysis because both expert-driven and automated methods can be biased or constrained by their training data, especially for novel or rare cell types.…

Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating…

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates. In practice, computational limits often rule out very large groups, so training proceeds with…

Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can…

A fundamental problem in robust learning is asymmetry: a learner needs to correctly classify every one of exponentially-many perturbations that an adversary might make to a test-time natural example. In contrast, the attacker only needs to…