Portrait de Shruti Joshi

Shruti Joshi

Doctorat - UdeM
Superviseur⋅e principal⋅e
Dhanya Sridhar
Sujets de recherche
Apprentissage de représentations
Causalité
Modèles génératifs
Site web
Google Scholar

Publications

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
Vitoria Barin Pacela
Shruti Joshi
Isabela Camacho
Simon Lacoste-Julien
David Klindt
The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under su… (voir plus)perposition, this encoding is a projection from a higher-dimensional concept space into a lower-dimensional activation space, and a linear decision boundary in the concept space need not remain linear after projection. In this setting, classical sparse coding methods with per-sample iterative inference leverage compressed sensing guarantees to recover latent factors. Sparse autoencoders (SAEs), on the other hand, amortise sparse inference into a fixed encoder, introducing a systematic gap. We show this amortisation gap persists across training set sizes, latent dimensions, and sparsity levels, causing SAEs to fail under out-of-distribution (OOD) compositional shifts. Through controlled experiments that decompose the failure, we identify dictionary learning -- not the inference procedure -- as the binding constraint: SAE-learned dictionaries point in substantially wrong directions, and replacing the encoder with per-sample FISTA on the same dictionary does not close the gap. An oracle baseline proves the problem is solvable with a good dictionary at all scales tested. Our results reframe the SAE failure as a dictionary learning challenge, not an amortisation problem, and point to scalable dictionary learning as the key open problem for sparse inference under superposition.
2026-03-29
arXiv (prépublication)
doi.org
arxiv.org
Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations
Shruti Joshi
Theo Saulus
Wieland Brendel
Philippe Brouillard
Dhanya Sridhar
Patrik Reizinger
Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with k… (voir plus)nown ground-truth factors. These metrics are assumed to reflect recovery up to the equivalence class guaranteed by identifiability theory. We show that this assumption holds only under specific structural conditions: each metric implicitly encodes assumptions about both the data-generating process (DGP) and the encoder. When these assumptions are violated, metrics become misspecified and can produce systematic false positives and false negatives. Such failures occur both within classical identifiability regimes and in post-hoc settings where identifiability is most needed. We introduce a taxonomy separating DGP assumptions from encoder geometry, use it to characterise the validity domains of existing metrics, and release an evaluation suite for reproducible stress testing and comparison.
2026-02-26
arXiv (prépublication)
doi.org
arxiv.org
Causality is Key for Interpretability Claims to Generalise
Shruti Joshi
Aaron Mueller
David Klindt
Wieland Brendel
Patrik Reizinger
Dhanya Sridhar
Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persis… (voir plus)t: findings that do not generalise, and causal interpretations that outrun the evidence. Our position is that causal inference specifies what constitutes a valid mapping from model activations to invariant high-level structures, the data or assumptions needed to achieve it, and the inferences it can support. Specifically, Pearl's causal hierarchy clarifies what an interpretability study can justify. Observations establish associations between model behaviour and internal components. Interventions (e.g., ablations or activation patching) support claims how these edits affect a behavioural metric (e.g., average change in token probabilities) over a set of prompts. However, counterfactual claims -- i.e., asking what the model output would have been for the same prompt under an unobserved intervention -- remain largely unverifiable without controlled supervision. We show how causal representation learning (CRL) operationalises this hierarchy, specifying which variables are recoverable from activations and under what assumptions. Together, these motivate a diagnostic framework that helps practitioners select methods and evaluations matching claims to evidence such that findings generalise.
2026-02-17
arXiv (prépublication)
doi.org
arxiv.org
Dynamic Inference with Neural Interpreters
Nasim Rahaman
Muhammad Waleed Gondal
Shruti Joshi
Peter Gehler
Yoshua Bengio
Francesco Locatello
Bernhard Schölkopf
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they ar… (voir plus)e less capable of systematic generalization to data drawn from unseen but related distributions, a feat that is hypothesized to require compositional reasoning and reuse of knowledge. In this work, we present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules, which we call \emph{functions}. Inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. The proposed architecture can flexibly compose computation along width and depth, and lends itself well to capacity extension after training. To demonstrate the versatility of Neural Interpreters, we evaluate it in two distinct settings: image classification and visual abstract reasoning on Raven Progressive Matrices. In the former, we show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner. In the latter, we find that Neural Interpreters are competitive with respect to the state-of-the-art in terms of systematic generalization
2020-12-31
NeurIPS (publié)
doi.org
openreview.net