36 citations · 113 across the 21 of their papers we have counts for
13 papers · 1 filter
The Best Optimizer Depends on Batch Size
Xingyu Dang, Kaiyue Wen, Sadhika Malladi
A plethora of new adaptive optimizers are designed to efficiently estimate and use minibatch gradient statistics to shape parameter updates, but they are typically benchmarked at a…
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Sadhika Malladi, Samy Jelassi, Dylan Foster +2
Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tu…
In Good GRACEs: Principled Teacher Selection for Knowledge Distillation
Abhishek Panigrahi, Bingbin Liu, Sadhika Malladi +2
Knowledge distillation is an efficient strategy to use data generated by large "teacher" language models to train smaller capable "student" models, but selecting the optimal teache…
Provable unlearning in topic modeling and downstream tasks
Stanley Wei, Sadhika Malladi, Sanjeev Arora +1
Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult.…
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
Yiding Jiang, Allan Zhou, Zhili Feng +2
The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across…
Progressive distillation induces an implicit curriculum
Abhishek Panigrahi, Bingbin Liu, Sadhika Malladi +2
Knowledge distillation leverages a teacher model to improve the training of a student model. A persistent challenge is that a better teacher does not always yield a better student,…
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Noam Razin, Sadhika Malladi, Adithya Bhaskar +3
Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a mode…
Preference Learning Algorithms Do Not Learn Preference Rankings
Angelica Chen, Sadhika Malladi, Lily H. Zhang +4
Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner…
The Marginal Value of Momentum for Small Learning Rate SGD
Runzhe Wang, Sadhika Malladi, Tianhao Wang +2
Momentum is known to accelerate the convergence of gradient descent in strongly convex settings without stochastic gradient noise. In stochastic optimization, such as training neur…
Fine-Tuning Language Models with Just Forward Passes
Sadhika Malladi, Tianyu Gao, Eshaan Nichani +4
Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a prohibitively large amount of memory. Zeroth-…
A Kernel-Based View of Language Model Fine-Tuning
Sadhika Malladi, Alexander Wettig, Dingli Yu +2
It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical…
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
Sadhika Malladi, Kaifeng Lyu, Abhishek Panigrahi +1
Approximating Stochastic Gradient Descent (SGD) as a Stochastic Differential Equation (SDE) has allowed researchers to enjoy the benefits of studying a continuous optimization traj…
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
Zhiyuan Li, Sadhika Malladi, Sanjeev Arora
It is generally recognized that finite learning rate (LR), in contrast to infinitesimal LR, is important for good generalization in real-life deep nets. Most attempted explanations…